Programming Question

Decision Support SystemsCollege of Computing and Informatics
1
Contents
o 1.2 – Changing Business Environments and Evolving Needs for Decision
Support and Analytics
o 1.3 – Decision-Making Processes and Computer Decision Support
Framework
o 1.4 – Evolution of Computerized Decision Support to Business
Intelligence/Analytics/Data Science
o 1.5 – Analytics Overview
o 1.6 – Artificial Intelligence Overview
o 1.7 – Convergence of Analytics and AI
o 1.8 – Overview of the Analytics Ecosystem
3
Weekly Learning Outcomes
1. Understand the need for computerized support of managerial decision
making
2. Understand the development of systems for providing decision-making
support
3. Recognize the evolution of such computerized support to the current
state of analytics/data science and artificial intelligence
4. Describe the business intelligence (BI) methodology and concepts
5. Understand the different types of analytics and review selected
applications
6. Understand the basic concepts of artificial intelligence (AI) and see
selected applications
4
7. Understand the analytics ecosystem to identify various key players and
Required Reading
 Chapter 1: “An overview of Decision Support system,
Business Intelligence, Analysis, and AI” from “Analytics,
Data Science, & Artificial Intelligence: Systems for Decision
Support”.
Recommended Video
 Understanding Decision Support Systems

 What is Business Intelligence (BI)?

5
1.2 Changing Business Environments and Evolving
Needs for Decision Support and Analytics
• The Decision Making Process
• The Influence of the External and Internal Environments on the Process
• Data and Its Analysis in Decision Making
• Technologies for Data Analysis and Decision Support
6
The Decision Making Process
• The business world is full of uncertainties and rapid changes.
• Thus, the decision making process can determine the success or failure
of an organization, and how well it performs.
• In the past decision making was based on creativity, instinct, and
experience.
• Now, decision making is more grounded in scientific approach, and
utilizes systematic quantitative methods.
7
The Decision Making Process (cont.)
Managers usually undergo the decision making process using the following
steps:
1. Understand the decision you have to make
2. Collect all the information (Define the problem)
3. Identify the alternatives (Construct a model & Identify possible solutions)
4. Evaluate the pros and cons
5. Select the best alternative (Compare, choose and recommend the best solution)
6. Make the decision
7. Evaluate the impact of your decision
8
The Influence of External & Internal Environments
•
Predicting the consequences and the future of any given decisions is
complex. This is due to the uncertainty that can arise from multiple factors
including:
1.
2.
3.
4.
•
Political Factors (E.g. government policies, political instability)
Economic Factors (E.g. competition, changing demand)
Sociological and psychological factors
Environment Factors
Because of these constant changes, the trial-and-error approach to
management is unreliable and unsustainable. Managers must begin to use the
new tools and techniques of their fields.
9
Data and Its Analysis in Decision Making
10
•
The amount of data doubles every two years.
•
Decision making process requires an organization to collect and analyze
vast stores of data.
•
Computer applications have moved from
transaction-processing and monitoring activities => to
problem analysis and solution applications.
•
These activities are done with cloud-based technologies, mostly accessed
through mobile devices.
Data and Its Analysis in Decision Making (cont.)
• The foundation of modern management lies in
1. analytics and BI tools such as data warehousing, data mining,
online analytical processing (OLAP), dashboards, and
2. the use of cloud-based systems for decision support.
11
Technologies for Data Analysis and Decision Support
•
The following developments have contributed to the growth of decision
support and analytics technologies:
1.
2.
3.
4.
5.
6.
7.
8.
Group communication and collaboration
Improved data management
Managing giant data warehouses & Big Data
Analytical Support
Overcoming cognitive limits in processing and storing information
Knowledge Management
Anywhere, anytime support
Innovation and artificial intelligence
12
1.3 Decision-Making Processes and
Computer Decision Support Framework
• Simon’s Process: Intelligence, Design, Choice, and Implementation Phases
• The Classical Decision Support System Framework
• DSS Application
• Characteristics of DSS
• Components of a Decision Support System
13
Simon’s Process: Intelligence, Design, and Choice
•
Decision-making process phases:
1. Intelligence: The decision maker examines reality, identifies and defines the
problem.
2. Design: A model representing the system is constructed by and then
validated.
1. making assumptions to simplify reality and
2. identifying relationships between variables.
3. Choice: Selection of a proposed solution to the model . This solution is
tested to determine its viability.
4. Implementation: Successful implementation results in solving the real
problem. Failure leads to a return to an earlier phase of the process.
14
15
The Classical Decision Support System Framework
• The framework for computerized decision support can be represented in a 3×3
matrix with two dimensions:
1. Type of decisions:
o Structured: Routine/repetitive problems for which standard solution methods exist
o Semi structured: Fall between structured and unstructured problems
o Unstructured: Complex problems where there are no clear, standard solution
methods
2. Types of controls:
o Strategic planning: Defining long-range goals/policies for resource allocation
o Management control: The efficient use of resources in the accomplishment of
organizational goals
o Operational control: the efficient and effective execution of specific tasks
16
17
DSS Application
Decision support
• Key difference between DSS and BI applications:
1. Business intelligence (BI) systems monitor situations and identify problems
and/or opportunities using analytic methods.
2. DSS is a methodology for supporting decision making:o It uses an interactive, adaptable computer-based information system
(CBIS) developed for supporting the solution to a specific unstructured
management problem.
o It uses data, provides a user-friendly interface, and incorporates the
decision maker’s insights.
o It includes models that developed through an interactive and iterative
process.
18
Characteristics of
DSS
19
Components of a Decision Support System
• A DSS can be composed of:
1. Data management subsystem
2. Model management
subsystem
3. User interface subsystem
4. Knowledge-based
management subsystem
20
1. Data Management Subsystem
•
The data management subsystem is
composed of the following elements:
1. DSS database
2. Database management system
3. Data directory
4. Query facility
•
It can be interconnected with the
corporate data warehouse (a repository
for corporate relevant decision-making
data)
21
2. Model Management Subsystem
•
The model management subsystem is a
component that includes quantitative models
that provide the
o system’s analytical capabilities and
o appropriate software management.
• The model management subsystem of a DSS
is composed of the following elements:
1.
2.
3.
4.
5.
22
Model base
MBMS (Model Base Management System)
Modeling language
Model directory
Model
execution,
integration,
and
command processor
3. The User Interface Subsystem
• The user is considered part of the system.
• The user communicates with and commands
the DSS through the user interface subsystem.
• The Web browser has been recognized as an
effective DSS GUI because it is
o flexible,
o user-friendly, and a
o gateway to almost all sources of necessary
information and data.
• Web browsers have led to the development
of portals and dashboards (front end of many
DSS).
23
4. The Knowledge-Based Management Subsystem
•
The knowledge-based management
subsystem provides intelligence
o to augment the decision maker’s own
intelligence
o to help understand a user’s query and
provide a consistent answer.
•
Interconnected with the organization’s
knowledge repository or connected to
thousands of external knowledge sources.
• User interface developments are closely
tied to the major new advances in their
knowledge-based systems.
24
1.4 Evolution of Computerized Decision Support to
Business Intelligence/Analytics/Data Science
• Evolution Of Computerized Decision Support
• Framework for Business Intelligence
• Architecture of BI
• The Origins and Drivers of BI
• Data Warehouse as a Foundation for Business Intelligence
• Transaction Processing versus Analytic Processing
• A Multimedia Exercise in Business Intelligence
25
Evolution Of Computerized Decision Support
26
Evolution Of Computerized Decision Support (cont.)
1. Management Information Systems (MIS): a variety of reports used to
understand and address the changing business needs and challenges.
2. Decision Support Systems (DSS): combination of individuals intellectual
resources with the capabilities of the computer to improve the quality of
decisions.
o DSS designed and developed specifically for executives and their decisionmaking needs
3. Executive Information Systems (EIS): the need for more versatile reporting
leads to the development of EISs;
o These systems were designed as graphical dashboards that allow decision
makers to keep track of the key performance indicators.
27
A Framework for Business Intelligence (BI)
• BI is an umbrella term that combines architectures, tools, databases, analytical
tools, applications, and methodologies.
• BI process is based on the transformation of data -> information -> decisions ->
actions
• BI’s major objective is to enable
1. interactive access to data (in real time),
2. data manipulation,
3. appropriate analyses.
• By analyzing historical and current data,
situations, and performances, decision
makers able to make more informed and
better decisions.
28
Architecture of BI
• BI has four major components:
1. Data Warehouse (DW) (with its source data)
2. Business Analytics (a collection of tools for manipulating, mining, and analyzing the
data in the DW)
3. BPM (for monitoring &
analyzing performance)
4. User Interface
29
The Origins and Drivers of BI
• Business cycle times are extremely compressed; faster, and more informed.
• Managers need the right information at the right time and in the right place (core
of the modern approaches to BI).
• Organizations are being driven to capture, understand, and harness their data to
support decision making and improve business operations.
• Legislation/regulations require leaders to document their business processes and
sign off on the validity of the information they report to stakeholders.
30
Data Warehouse (DW) as a Foundation for BI
• BI systems rely on DWs as the information source for creating insight and
supporting managerial decisions.
• DW is a subject-oriented, integrated, time-variant, nonvolatile collection of data
in support of management’s decision-making process.
• The three main types of data warehouses are:
o Data Marts (DM): a subset of a DW, typically consisting of a single subject area
o Operational Data Stores (ODS): provides a form of customer information file
whose contents are updated throughout the course of business operations.
o Enterprise Data Warehouses (EDW): a large-scale data warehouse used across
the enterprise for decision support.
31
Data Warehouse (DW) as a Foundation for BI (cont.)
• Data from many different sources can be extracted, transformed, and loaded into
a DW for further access and analytics for decision support.
• Data is structured to
be available in a form
ready for analytical
processing activities:
o OLAP,
o data mining,
o querying,
o reporting,
o decision support
applications
32
Transaction Processing versus Analytic Processing
• Transaction processing systems are constantly involved in handling updates
to what may be known as operational databases.
• OLTP (OnLine Transaction Processing) systems handle a company’s routine
ongoing business, where the computer responds immediately to user
requests.
• The OLTP system is efficient for transaction processing, but inefficient for enduser ad hoc reports, queries, and analysis.
• In contrast, a DW is typically a distinct system that provides storage for data
that will be used for analysis by OLAP (OnLine Analytical Processing) systems.
33
Multimedia Exercise in Business Intelligence
• The fundamental reasons for investing in BI must be aligned with the
company’s business strategy.
• BI improve company business processes and transforming it to be more data
driven.
• BI tools are sometimes integrated among themselves, resulting in six key
trends:
1.
2.
3.
4.
5.
6.
34
Big Data
Focus on customer experience as opposed to just operational efficiency.
Mobile and even newer user interfaces—visual, voice, mobile.
Predictive and prescriptive analytics, machine learning, artificial intelligence.
Migration to cloud.
Much greater focus on security and privacy protection.
1.5 Analytics Overview
• Overview
• Descriptive, Predictive, Prescriptive Analytics
• Big Data
35
Analytics Overview
• Analytics is the process of developing actionable/recommendations for actions
based on insights generated from historical data.
• To solve real problems analytics represents the combination of
o computer technology +
o management science techniques +
o statistics.
36
Descriptive, Predictive, Prescriptive Analytics
• Three types of analytics:
1. Descriptive
2. Predictive
3. Prescriptive
37
Big Data
• Big Data refers to data that cannot be stored in a single storage unit.
• Different forms:
o structured
o unstructured
• Characteristics of big data:
o volume
o velocity
o variety
• These are evolving quickly to encompass stream analytics, IoT, cloud
computing, and deep learning– enabled AI.
38
Big Data (cont.)
• There are two aspects to managing data on this scale:
1.
Storing:
o an extremely expensive storage solution vs. store data in chunks on
different machines connected by a network.
o Hadoop Distributed File System (HDFS): store a copy or two of this chunk in
different locations on the network, both logically and physically.
2.
Processing:
o To process vast amounts of data computation done by one powerful
computer vs. processing data sets with a parallel distributed algorithm on a
cluster
o MapReduce programming paradigm
39
1.7 Artificial Intelligence Overview
• What Is Artificial Intelligence?
• The Major Benefits of AI
• The Landscape of AI
• The Three Flavors of AI Decisions
• Technology Insights 1.1
40
What Is Artificial Intelligence (AI)?
• The major goal of AI is to create intelligent machines that can do tasks
currently done by people.
• AI tasks include
o reasoning,
o thinking,
o learning, and
o problem solving.
• AI can also be defined as:
o Technology that can learn to do things better over time.
o Technology that can understand human language.
41
o Technology that can answer questions.
The Major Benefits of AI
• Significant reduction in the cost of performing work. This reduction continues
over time while the cost of doing the same work manually increases with
time.
• Work can be performed much faster.
• Work is consistent in general, more consistent than human work.
• Increased productivity and profitability as well as a competitive advantage
are the major drivers of AI.
42
The Landscape of AI
• We defined the landscape/ecosystem of AI into 5 categories:
1. Major Technologies: machine learning, deep learning, intelligent agents
2. Knowledge-Based Technologies: expert systems, recommendation engines, chatbots.
3. Biometric-Related Technologies: natural language processing, image recognition
4. Support Theories, Tools, & Platforms:
computer science, cognitive science,
mathematics, statistics, sensors, augmented
reality, neural networks, APIs, knowledge
management.
5. AI Applications: smart cities, smart homes,
automatic decisions, translation, robotics,
fraud detection.
43
The Landscape of AI (cont.)
• AI Applications are in area like
o business,
o medicine & healthcare
o transportation
o education
• AI field divided into two major categories of applications:
1. Narrow (Weak): Focuses on one narrow field (Domain). Examples
include SIRI and Alexa that operate in limited, predefined areas.
2. General (Strong): To exhibit real intelligence, machines need to perform
the full range of human cognitive capabilities (e.g. reasoning and
problem solving).
44
The Three Levels of AI Systems
• The capabilities of AI systems can be divided into three levels:
1. Assisted Intelligence: equivalent mostly to the weak AI, which works only in
narrow domains. It requires clearly defined inputs and outputs such as
monitoring systems.
2. Autonomous AI: in the realm of the strong AI but in a narrow domain.
Eventually, the computer will take over as very narrow expert and have absolute
decision-making power.
3. Augmented Intelligence: between assisted and autonomous. The technology
focuses on augmenting computer abilities to extend human cognitive abilities,
resulting in high performance. Examples: Cybercrime fighting, E-Commerce
decisions, High-frequency stock market trading.
45
Technology Insights
•
Differences between traditional and augmented AI:
1. Augmented machines extend rather than replace human decision making
2. Augmentation excels in solving complex human and industry problems in
specific domains in contrast with strong, general AI.
3. In contrast with a “black box” model of some AI and analytics, augmented
intelligence provides insights and recommendations, including
explanations.
46
1.7 Convergence of Analytics and AI
• Major Differences between Analytics and AI
• Why Combine Intelligent Systems?
• How Convergence Can Help?
• Big Data Is Empowering AI Technologies
• The Convergence of AI and the IoT
• The Convergence with Blockchain and Other Technologies
47
Major Differences between Analytics and AI
• Analytics processes historical data using statistical, management science and
other computational tools to describe situations, predict results, and propose
recommendations for solutions to problems.
• AI’s major objective is to mimic the manner in which people think, learn,
reason, make decisions, and solve problems.
• The emphasis in AI is on knowledge and intelligence as major tools for solving
problems rather than relying on computation, which we do in analysis.
48
Why Combine Intelligent Systems?
• Analytics, AI and their different technologies have limitations, resulting in only a
small chance that they can be used to reach organizational excellence.
• There are several reasons for this situation including:
1. Predictive models have unintended effects
2. The results of analytics may be good for some applications but not for others
3. Models are as good as their input data and assumptions
4. Data could be incomplete/inaccurate.
5. Data collected from different sources can vary in format and quality.
• A major reason for the high failure rate of AI is that some of its technologies
need a large amount of data (Big Data). Without this continuous flow of data,
there would not be good learning in AI.
49
How Convergence Can Help?
• BI and its analytics answer most of the why and what questions regarding the
sufficiency of problem solving.
• The next generation of business intelligence platforms will use AI to
automatically locate, visualize, and narrate important things. This can also be
used to create automatic alerts and notifications.
• Machine learning and deep learning can support analytics by conducting
pattern recognition and more accurate predictions. AI will help to compare
actual performance with the predicted one.
50
Big Data Is Empowering AI Technologies
• Technologies and methods that enable capturing, cleaning, and analyzing Big
Data, can also enable companies to make real-time decisions.
• The availability of new Big Data analytics enables new capabilities in AI
technologies that were not possible until recently.
• Big Data can empower AI due to:
o The new capabilities of processing Big Data at a much reduced cost.
o The availability of large data sets online.
o The scale up of algorithms, including deep learning, is enabling powerful
AI capabilities.
51
The Convergence of AI and the IoT
• The IoT collects a large amount of data from sensors and other “things.”
These data need to be processed for decision support.
• Combining AI and IoT can
o lead to the “next-level solutions and experiences.” The emphasis in such
combination is on learning more about customers and their needs.
o facilitate competitive analysis and business operation.
• Three examples of combining AI and IoT:
o The smart thermostat of Nest Labs
o Automated vacuum cleaners
o Self-driving vehicles
52
The Convergence with Blockchain & Other
Technologies
• Several experts raise the possibility of the convergence of AI, analytics, and
blockchain. This convergence also can include the IoT.
• The blockchain technology can add security to data shared by all parties in a
distributed network, where transaction data can be recorded.
• This combination can be very useful in complex applications such as
autonomous vehicles.
53
1.8 Overview of the Analytics Ecosystem
• Analytics Ecosystem
54
Analytics Ecosystem
• Purpose of analytics
ecosystem is to be aware of
organizations, new offerings,
and opportunities in sectors
allied with analytics.
• The components of the
ecosystem are represented
by the petals of an analytics
flower.
55
• Grouped into categories:
o inner petals
o outer petals
o seed
Main Reference
 Chapter 1: “An overview of Decision Support system, Business
Intelligence, Analysis, and AI” from “Analytics, Data Science, & Artificial
Intelligence: Systems for Decision Support”.
Week self-review exercises
 Application Case 1.1 to Application Case 1.10 from “Analytics, Data Science, &
Artificial Intelligence: Systems for Decision Support”
56
Decision Support Systems
College of Computing and Informatics
1
Contents
o 2.2 – Introduction to Artificial Intelligence
o 2.3 – Human and Computer Intelligence
o 2.4 – Major AI Technologies and Some Derivatives
o 2.5 – AI Support for Decision Making
o 2.6 – AI Applications in Accounting
o 2.7 – AI in Human Resource Management (HRM)
o 2.8 – AI in Marketing, Advertising, and CRM
o 2.9 – AI Applications in Financial Services
o 2.10 – AI Applications in Production-Operation Management (POM)
3
Weekly Learning Outcomes
1. Understand the concepts of artificial intelligence (AI)
2. Become familiar with the drivers, capabilities, and benefits of AI
3. Describe human and machine intelligence
4. Describe the major AI technologies and some derivatives
5. Discuss the manner in which AI supports decision making
6. Describe AI applications in accounting, human resource management,
marketing, financial Services and in Production-Operation
Management (POM)
4
Required Reading

Chapter 2: “Analytics, Data Science, & Artificial Intelligence: Systems for
Decision Support” from “Analytics, Data Science, & Artificial Intelligence:
Systems for Decision Support”.
Recommended Reading
 AI-powered decision support systems, what are they?
https://blog.pwc.lu/ai-powered-decision-support-systems-what-are-they/
Recommended Videos
 Artificial intelligence and decision-making (by Thorbjørn
Knudsen)

5
2.2 Introduction To Artificial Intelligence
• Definition of AI
• Major Characteristics of AI Machines
• Major Elements of AI
• AI Applications
• Major Goals of AI
• Drivers of AI
• Benefits of AI
• Some Limitations of AI Machines
• Three Flavors of AI Decisions
• Artificial Brain
6
Definition of AI
• Artificial intelligence has several definitions that is concerned with two basic
ideas:
o The study of human thought processes (to understand what intelligence
is)
o The representation and duplication of those thought processes in
machines (e.g., computers, robots)
• Another definition of AI is “the capabilities of a machine to imitate intelligent
human behavior”
7
Major Characteristics of AI Machines
• There is an increasing trend to make computers “smarter”.
o Web 3.0 enables computerized systems that exhibit more intelligence than
Web 2.0.
• Several applications are already based on multiple AI techniques.
o Machine translation of languages is helping people who speak different
languages to collaborate in real time as well as to buy online products that
are advertised in different languages.
8
Major Elements of AI
• AI components can be divided into two groups: Foundations, and Technologies &
Applications.
9
AI Applications
Smart or intelligent applications include:
• Machines to answer customers’ questions asked in natural languages
• Knowledge-based systems which can provide advice, assist people to make
decisions, and even make decisions on their own
• Automatic generating of online purchasing orders and arranging fulfillment of
orders placed online.
• Shipping prices are determined automatically based on the dimensions,
weight, and packaging.
10
Major Goals of AI
• The overall goal of AI is to create intelligent machines that are capable of
executing a variety of tasks currently done by people.
• AI machines should be able to reason, think abstractly, plan, solve problems,
and learn.
• Some specific goals are to:
o Perceive and properly react to changes in the environment that influence
specific business processes and operations
o Introduce creativity in business processes and decision making
11
Drivers of AI
• The use of AI has been driven by the following:
o People’s interest in smart machines and artificial brains
o The low cost of AI applications versus the high cost of manual labor (doing the
same work)
o The desire of large tech companies to capture competitive advantage and
market share of the AI market and their willingness to invest billions of dollars
in AI
o The pressure on management to increase productivity and speed
o The availability of quality data contributing to the progress of AI
o The increasing functionalities and reduced cost of computers in general
o The development of new technologies, particularly cloud computing
12
Benefits of AI
o AI has the ability to complete certain tasks faster than humans.
o The consistency of AI work. AI machines do not stop, or sleep.
o AI systems allow for continuous improvement projects.
o AI can be used for predictive analysis via its capability of pattern recognition.
o AI can manage delays and blockages in business processes.
o AI machines can work autonomously or be assistants to humans.
o AI machines can learn, improve its performance, and work in hazardous environments.
o AI machines can facilitate innovations by human (i.e., support research and development)
o AI excels in fraud detection and in security facilitations.
o AI can free employees to work on more complex and productive jobs.
o AI can solve difficult problems that previously were unsolved.
13
Some Limitations of AI Machines
• The following are the major limitations of AI machines:
o Lack human touch and feel
o Lack attention to non-task surroundings
o Can lead people to rely on AI machines (e.g., people may stop to think on
their own)
o Can be programmed to create destruction
o Can cause many people to lose their jobs
o Can start to think by themselves, diminishing with time. However, risks
exist. Therefore, it is necessary to properly causing significant damage
• Some of the limitations are diminishing with time. However, risks exist.
Therefore, it is necessary to improve AI development and minimize the risks.
14
Artificial Brain
• The artificial brain is a machine that is desired to be as intelligent, creative,
and self-aware as humans. To date, no one has created such a machine.
• The following are some differences between traditional and augmented AI:
o Augmented machines extend rather than replace human decision making
o Augmentation excels in solving complex human and industry problems in
specific domains in contrast with strong, general AI.
o In contrast with a “black box” model of some AI and analytics, augmented
intelligence provides insights and recommendations, including
explanations.
15
2.3 Human and Computer Intelligence
• A. What Is Intelligence?
• B. How Intelligent Is AI?
• C. Measuring AI
16
What Is Intelligence?
• Intelligence is a broad term measured by an IQ test.
• To understand what artificial intelligence is, it is useful to first examine those
abilities that are considered signs of human intelligence:
o Learning or understanding from experience
o Making sense out of ambiguous, incomplete, or even contradictory
messages and information
o Responding quickly and successfully to a new situation
o Understanding/inferring in a rational way, and solving problems
o Applying knowledge to manipulate environments and situations
o Recognizing & judging the relative importance of elements in a situation
17
How Intelligent Is AI?
• AI machines have demonstrated superiority over humans in playing complex
games such as chess, Jeopardy!, and Go by defeating the world’s best players.
• Despite this many AI applications still show significantly less intelligence than
humans.
18
Measuring AI
• The Turing Test is a well-known attempt to measure the intelligence level of AI
machines.
• It aims to determine whether a computer exhibits intelligent behavior. A computer
can be considered smart only when a human interviewer asking the same questions
to both an unseen human and an unseen computer cannot determine which is
which.
• To pass the Turing Test, a computer needs
to be able to understand a human language
(NLP), to possess human intelligence (e.g.,
have a knowledge base), to reason using its
stored knowledge, and to be able to learn
from its experiences (machine learning).
19
2.4 Major AI Technologies And Some
Derivatives
• Intelligent Agents
• Machine Learning
• Deep Learning
• Machine and Computer Vision
• Robotic Systems
• Natural Language Processing
• Knowledge and Expert Systems
and Recommenders
• Chatbots
20
• Emerging AI Technologies
Intelligent Agents
• An intelligent agent (IA) is a small computer software program that observes
and acts upon changes in its environment by running specific tasks
autonomously.
• An IA directs an agent’s activities to achieve specific goals related to the changes
in the surrounding environment.
• IAs have the ability to learn by using their knowledge
Example 1: An example of an intelligent software agent is a virus detection program.
It resides in a computer, scans incoming data, and removes viruses automatically
while learning to detect new virus types and detection methods.
21
Example 2: Allstate Business Insurance uses an intelligent agent to reduce call center
traffic and provide human insurance agents during the rate-quoting process with
business customers
Machine Learning
• Machine Learning (ML) is a discipline concerned with design & development of
algorithms that allow computers to learn based on incoming data.
• ML allows computer systems to monitor and sense their environment, so that the
machines can adjust their behavior to deal with the changes
• ML scientists teach computers to identify patterns and make connections by showing
the machines a large volume of examples and related data.
• ML used for predicting, recognizing patterns, & supporting decision makers. An
example is computers detecting credit card fraud.
• ML applications are expanding due to the availability of Big Data sources, especially
those provided by the IoT.
22
Deep Learning
• One subset of machine learning is called deep learning; a technology tries to
mimic how the human brain works.
• Deep learning (DL) uses artificial neural technology and deals with complex
applications that regular machine learning and AI technologies can not handle.
• For example, DL is a key technology in autonomous vehicles by helping to
interpret road signs and road obstacles.
• DL is mostly useful in real-time interactive applications in the areas of
machine vision, scene recognition, robotics, and speech and voice processing.
23
Machine and Computer Vision
• Machine vision includes “technology and methods used to provide imagingbased automated inspection and analysis for applications such as robot
guidance, process control, autonomous vehicles, and inspection.”
• Computer vision “is an interdisciplinary field that deals with how computers
can be made for gaining high-level understanding from digital images or videos.
From the perspective of engineering, it seeks to automate tasks that the
human visual system can do.”
24
Machine and Computer Vision
• The two technologies are combined with image processing that facilitates
complex applications, such as visual quality control.
• Applied area of machine vision is scene recognition, done by computer vision.
• Video analytics is a derivative application of computer vision, where techniques
are applied to videos to enable pattern recognition and identify events.
• Example of Applications:
o The machine vision wood identification project developed a prototype machine
vision system for wood identification to help identify illegal logging.
o AI computer vision mixed with deep learning identifies illegal animal poachers.
o Facial recognition that employ smart glasses to identify potential suspects.
25
Robotic Systems
• A robot is a device guided by a program to perform manual/mental tasks.
• An “intelligent” robot has a sensory apparatus (e.g., camera) to collects
information about the surroundings and can respond to the changes in the
environment.
• Autonomous robots (programmed to do tasks completely on their own, even
repair themselves), are equipped with AI intelligent agents.
• Example: Walmart Is Using Robots
o In Walmart, 2-foot-tall robots use cameras/sensors
to scan the shelves for misplaced, missing,
or mispriced items. The results are transmitted to
humans for corrective actions. The robots carry
out their tasks faster and frequently more
accurately than humans.
26
Natural Language Processing
• Natural language processing (NLP) allows users to communicate
with a computer in their native language. NLP includes two subfields:
o NLP that investigates methods of enabling computers to
comprehend instructions or queries provided in English or other
human languages.
o NLP generation that strives to have computers produce ordinary
spoken language so that people can understand the computers
more easily.
• Speech/Voice Understanding: recognition & comprehension of
spoken languages by a computer. This has been adopted in
automated call centers.
27
• Machine Translation of Languages: uses computer programs to
translate words and sentences from one language to another.
Knowledge and Expert Systems and Recommenders
• These systems are computer programs that store knowledge, which their
applications use to generate expert advice and/or perform problem solving.
• Knowledge-based expert systems help people to verify information and make
certain types of automated routine decisions.
• Recommendation systems are knowledge-based systems that make
recommendations to people. Another knowledge system is chatbots.
• Knowledge Sources And Acquisition For Intelligent:
Intelligent systems must gain knowledge through
knowledge acquisition.
28
• Knowledge acquisition includes extracting and
structuring knowledge from data, and
then experts may be used to verify it.
Chatbots
• Robots come in several shapes and types, of which is a chatbot. A chatbot is a
conversional robot that is used for chatting with people using NLP technology.
• Depending on the purpose of the chat, which can be done in writing or by
voice, bots can be in the form of intelligent agents that retrieve information or
personal assistants that provide advice.
29
Emerging AI Technologies
• Several new AI technologies are emerging. Here are a few examples:
o Effective computing. Technologies that detect emotional conditions of
people and suggest how to deal with discovered problems
o Biometric analysis. Technologies that verify an identity based on unique
biological traits that are compared to stored ones (e.g., facial recognition).
• Cognitive Computing: The application of knowledge derived from cognitive
science so that computers can exhibit and/or support decision-making and
problem-solving capabilities.
• Augmented Reality: Augmented reality (AR) refers to the real time integration of
digital information with a users environment (mostly vision and sound). The
technology provides a real-world interactive experience with the environment.
30
2.5 AI Support For Decision Making
• Issues and Factors in Using AI in Decision Making
• AI Support of the Decision-Making Process
• Automated Decision Making
31
Issues and Factors in Using AI in Decision Making
• These factors determine the justification of AI usage and its chance of success:
o The nature of the decision (E.g., routine decisions = likely automated)
o The method of support, what technologies are used
• Cost-benefit & Risk Analyses: necessary for large-scale decisions, but hard to
compute with AI models due to difficulties in measuring costs, risks, & benefits.
• Using Business Rule: AI systems can be based on business rules, whose quality
determines that of the automated.
• AI Algorithms: are the basis for automated decisions & decision support.
• Speed: Decision automation is dependent on the speed decisions needs to be
made. Some decisions takes too much time to get all the relevant input data.
32
AI Support of the Decision-Making Process
 AI support can be applied to the various steps of the decision-making process:
33
1.
Problem Identification: collecting data through technology that can be used by AI
algorithms. Performance levels of machines are compared to standards, and trend
analysis can point to opportunities.
2.
Generating/Finding Alternative Solutions: matching problem characteristics with best
practice, or proven solutions stored in databases. Tools such as case-based reasoning
and neural computing are for this purpose.
3.
Selecting a Solution: evaluate proposed solutions, predict future impacts, asses chance
of success, or predict a reply to actions taken by a competitor.
4.
Implementing the Solutions: demonstrates the superiority of proposals and to assess
resistance to changes.
Automated Decision Making
• The process of automated decision making starts with knowledge acquisition
and creation of a knowledge repository.
• The system generates and submits responses to user’s questions. Solutions
are evaluated to improve the knowledge repository, and complex situations
are forwarded to humans.
• Companies use automated decision making for both their external operations
(e.g., sales) and internal operations (e.g., resource allocation)
Example: Supporting Nurses’ Diagnosis Decisions
• Researchers used AI tools to conduct data mining to predict the probable
success of automated nursing diagnoses based on patient characteristics.
34
Main Reference

Chapter 2: “Analytics, Data Science, & Artificial Intelligence: Systems for Decision
Support” from “Analytics, Data Science, & Artificial Intelligence: Systems for
Decision Support”.
Week self-review exercises
 Application Case 2.1 – 2.7 from “Analytics, Data Science, & Artificial Intelligence: Systems
for Decision Support”
35
Decision Support Systems
College of Computing and Informatics
1
Contents
o 3.7 – Business Reporting
o 3.8 – Data Visualization
o 3.9 – Different Types of Charts and Graphs
o 3.10 – Emergence of Visual Analytics
o 3.11 – Information Dashboards
o Analyzing data with pivottables and pivotcharts using excel
3
3.7 Business Reporting
•
Overview
7
Overview
• Decision makers need information to make accurate and timely decisions.
• Information is usually provided to decision makers in the form of a written
report that contains organized information referring to specific time periods.
• Business reports can fulfill many different functions:
o To ensure that all departments are functioning properly
o To provide information
o To provide the results of an analysis
o To persuade others to act
o To create an organizational memory
8
Overview (cont.)
• Business reporting (also called OLAP or BI) is an essential part of the larger
drive toward improved, evidence-based, optimal managerial decision making.
• The foundation of these business reports is various sources of data coming
from both inside and outside the organization (OLTP systems).
• Creation of these reports involves extract, transform, and load (ETL)
procedures in coordination with a data warehouse and reporting tools.
• This reporting process involves querying structured data sources, which were
created using different logical data models and data dictionaries, to produce a
human-readable, easily digestible report.
9
Overview (cont.)
• These types of business reports allow managers to stay informed and
involved, review options and alternatives, and make informed decisions.
• Metric Management Reports: In many organizations, business performance is
managed through outcome-oriented metrics. For external groups, these are
service-level agreements. For internal management, they are key performance
indicators (KPIs).
• Dashboard-type Reports: A popular idea in business reporting has been to
present a range of different performance indicators on 1 page like a
dashboard.
10
• Balanced Scorecard–type Reports: This method attempts to present an
integrated view of success in an organization. In addition to financial
performance, balanced scorecard–type reports also include customer, business
process, and learning and growth perspectives.
3.8 Data Visualization
•
•
11
Overview
History of Data Visualization
Overview
• Data visualization has been defined as “the use of visual representations to
explore, make sense of, and communicate data”.
• Information is the aggregation, summarization, and contextualization of data,
what is portrayed in visualizations is the information, not the data.
• Data visualization is closely related to the fields of information graphics,
information visualization, scientific visualization, and statistical graphics.
• Until recently, the major forms of data visualization available in both BI
applications have included charts and graphs as well as the other types of
visual elements used to create scorecards and dashboards.
12
History of Data Visualization
• Although visualization has not been widely
recognized as a discipline until fairly recently, today’s
most popular visual forms date back a few centuries.
• Companies and individuals are interested in data;
that interest has in turn sparked a need for visual
tools that help them understand it.
• Countless applications, tools, and code libraries help
people collect, organize, visualize, understand data.
• The future of data visualization holds more 3D
imaging, experience with multidimensional data, and
holographs of information.
13
3.9 Different Types of Charts and
Graphs
•
•
•
14
Basic Charts & Graphs
Specialized Charts & Graphs
Which Chart/Graph should you use?
Basic Charts & Graphs
• Line Chart: Line charts show the relationship between two
variables; they are most often used to track changes or
trends over time.
• Bar Chart: Effective when you have nominal/numerical data
that splits into different categories so you can quickly see
comparative results and trends.
• Pie Chart: Pie charts illustrate relative proportions of a
specific measure. If the number of categories is more than a
few consider using a bar chart.
15
Basic Charts & Graphs
• Histogram: Histograms are used to show the frequency
distribution of 1+ variables. The x-axis shows categories,
and the y-axis the frequencies.
• Scatter Plot: The scatter plot is often used to explore the
relationship between two or three variables (in 2D or 3D
visuals).
• Bubble Chart: The bubble chart is an enhanced scatter
plot. By varying the circles, one can add additional data
dimensions, offering more enriched data.
16
Specialized Charts & Graphs
• Geographic Map: Used when the data set includes
any kind of location data.
• Gantt Chart: A special case of bar charts used to
portray project timelines, project tasks/activity
durations, and overlap among the tasks/activities.
• PERT Chart: developed primarily to simplify the
scheduling of large/complex projects. A PERT chart
shows relationships among project activities/tasks.
17
Specialized Charts & Graphs
• Bullet: Used to show progress towards a goal. It is a
variation of a bar chart.
• Tree Map: A tree map displays hierarchical data as a
set of nested rectangles. Each branch of the tree is
given a rectangle, which is then tiled with smaller
rectangles representing subbranches.
18
Specialized Charts & Graphs
• Heat Map: A visual that illustrates the comparison
of continuous values across two categories using
color.
• Highlight Table: Two-dimensional tables with cells
populated with numerical values and gradients of
colors.
19
Which Chart/Graph should you use?
• The capabilities of the charts helps select the proper chart for a specific task..
20
Which Chart/Graph should you use?
• The taxonomic structure is organized around the purpose of the chart or graph.
• The taxonomy divides the purpose into four different types—relationship,
comparison, distribution, and composition—and further divides the branches into
subcategories based on the number of variables involved and time dependency of
the visualization.
• The current trend is to combine and animate these charts for better-looking and
more intuitive visualization of today’s complex and volatile data sources.
21
3.10 Emergence of Visual Analytics
•
•
•
•
•
Overview
Visual Analytics
What is a good story?
Analysis as a Story
High-Powered Visual Analytics Environments
22
Overview
• In BI and analytics, the key challenge of visualization is representation of large,
complex data sets with multiple dimensions and measures.
• Typical charts, graphs, and visual elements used involve two dimensions,
sometimes three, and fairly small subsets of data sets.
• In contrast, data in visual systems reside in a data warehouse. At a minimum,
these warehouses involve a range of dimensions (e.g., product, location,
organizational structure, time), a range of measures, and millions of data cells.
• In an effort to address these challenges, a number of researchers have
developed a variety of new visualization techniques.
23
Visual Analytics
• What is meant by visual analytics is the combination of visualization and
predictive analytics.
• Information visualization is aimed at answering “What happened?” and
“What is happening?” and is closely associated with BI (routine reports,
scorecards, and dashboards)
• Visual analytics is aimed at answering “Why is it happening?” and “What is
more likely to happen?” and is usually associated with business analytics
(forecasting, segmentation, correlation analysis).
24
What is a Good Story?
• Most people can easily remember a funny story because it contains certain
characteristics and components, such as:
o Good characters.
o The character is faced with a challenge that is difficult but believable.
o There are hurdles that the character overcomes.
o The outcome or prognosis is clear by the end of the story.
o The situation may not be resolved—but the story has a clear endpoint.
25
Analysis as a Story
• With story elements in place, write out the storyboard, that represents the
structure and form of your story.
• The storyboard will help you think about the best analogies, clearly set up
challenge or opportunity, and finally see the flow and transitions needed.
• By following the best practices, you can get people to focus on your message:
o Think of your analysis as a story—use a story structure.
o Be authentic—your story will flow.
o Be visual—think of yourself as a film editor.
o Make it easy for your audience and you.
o Invite and direct discussion.
26
High-Powered Visual Analytics Environments
• There is a movement towards highly efficient visualization systems. SAS Visual
Analytics, is a very high-performance computing, in-memory solution for
exploring massive amounts of data in a very short time.
• Benefits proposed by the SAS analytics platform are the following:
o Empowers users with data exploration techniques and approachable analytics
to drive improved decision making.
o Has easy-to-use, interactive interfaces that broaden the audience for analytics.
o Improves information sharing and collaboration.
o Liberates IT by giving users a new way to access the information they need.
o Provides room to grow at a self-determined pace.
27
E. High-Powered Visual Analytics Environments
28
3.11 Information Dashboards
•
•
•
•
•
•
•
•
•
•
•
29
Overview
Dashboard Design
Best Practices in Dashboard Design
Benchmark KPIs with Industry Standards
Wrap the Dashboard Metrics with Contextual Metadata
Validate the Dashboard Design by a Usability Specialist
Prioritize and Rank Alerts/Exceptions Streamed to the Dashboard
Enrich the Dashboard with Business-User Comments
Present Information in Three Different Levels
Pick the Right Visual Construct Using Dashboard Design Principles
Provide for Guided Analytics
Overview
• Information dashboards are common
components of BI platforms, business
performance management systems, and
measurement software suites.
• Dashboards provide visual displays of
important information arranged on a single
screen so that the information can be
digested at a single glance.
• This executive dashboard shows functional
groups surrounding the products intended to
give executives a quick and accurate idea of
what is going on within the organization.
30
Dashboard Design
• Today, it would be rather unusual to see a large company using a BI system
that does not employ some sort of performance dashboards.
• The most distinctive feature of a dashboard is its three layers of information:
o Monitoring: Graphical, abstracted data to monitor key performance metrics
o Analysis: Summarized dimensional data to analyze the root cause of problems
o Management: Data that identifies actions needed to resolve a problem
• “The fundamental challenge of dashboard design is to display all the required
information on a single screen.”
31
• Because of these layers, dashboards pack a large amount of information into a
single screen
Best Practices in Dashboard Design
• Data is one of the most important things to focus on in dashboard design.
• Even if a dashboard’s appearance looks professional, is aesthetically pleasing, and
includes graphs and tables, it is also important to ask about the data:
o Are they reliable?
o Are they timely?
o Are any data missing?
o Are they consistent across all dashboards?
32
Benchmark KPIs with Industry Standards
• Many customers want to know if the metrics they are measuring are the right
metrics to monitor.
• Sometimes customers have found that the metrics they are tracking are not
the right ones to track.
• Doing a gap assessment with industry benchmarks aligns you with industry
best practices.
33
Wrap the Dashboard Metrics with Contextual Metadata
• When a report or a visual dashboard/scorecard is presented to business users,
questions remain unanswered. The following are some examples:
o Where did you source these data?
o While loading the data warehouse, what percentage of the data was rejected/
encountered data quality problems?
o Is the dashboard presenting “fresh” information or “stale” information?
o When was the data warehouse last refreshed?
o When is it going to be refreshed next?
34
o Were any high-value transactions that would skew the overall trends rejected
as a part of the loading process?
Validate the Dashboard Design by a Usability Specialist
• In most dashboard environments, the dashboard is designed by a tool
specialist without giving consideration to usability principles.
• Even though it is a well-engineered data warehouse that can perform well,
many business users do not use the dashboard.
• It is perceived as not being user friendly, leading to poor adoption of the
infrastructure and change management issues.
• Up-front validation of the dashboard design by a usability specialist can
mitigate this risk.
35
Prioritize and Rank Alerts/Exceptions Streamed to the Dashboard
• There are tons of raw data, having a mechanism by which important
exceptions are proactively pushed to the information consumers is important.
• A business rule can be codified, which detects the alert pattern of interest.
• It can be coded into a program, using database-stored procedures, which crawl
through the fact tables and detect patterns needing immediate attention.
• This way, information finds the business user as opposed to the business user
polling the fact tables for the occurrence of critical patterns.
36
Enrich the Dashboard with Business-User Comments
• In the event that dashboard information is presented to multiple business
users, a small text box can be provided to capture the comments from an end
user’s perspective.
• This can often be tagged to the dashboard to put the information in context,
adding perspective to the structured KPIs being rendered.
37
Present Information in Three Different Levels
• Information can be presented in three layers depending on the granularity of
the information:
o the visual dashboard level
o the static report level
o the self-service cube level
• When a user navigates the dashboard, a simple set of 8 to 12 KPIs can be
presented, which would give a sense of what is going well and what is not.
38
Pick Right Visual Construct Using Dashboard Design Principles
• In a dashboard, some information is presented best with bar charts, or timeseries line graphs.
• When presenting correlations, a scatter plot is useful. Sometimes merely
rendering it as simple tables is effective.
• Once the dashboard design principles are explicitly documented, all the
developers working on the front end can adhere to the same principles while
rendering the reports and dashboard.
39
Provide for Guided Analytics
• In an organization, users can be at various levels of analytical maturity.
• The capability of the dashboard can be used to guide a business user to access
the same navigational path as that of an analytically savvy business user.
40
8.2 Model-Based Decision Making
6
•
Prescriptive Analytics Model Examples
•
Identification of the Problem and Environmental Analysis
•
Model Categories
•
Current Trends in Modeling
Prescriptive Analytics Model Examples
• Modeling is a key element for prescriptive analytics.
• Depending on the problem we are addressing, there are many classes of
models, and there are often many specialized techniques for solving each one.
• Prescriptive analytics involves the application of mathematical models,
sometimes the term data science is more commonly associated with the
application of such mathematical models.
7
Identification of the Problem and Environmental Analysis
• It is important to analyze the scope of the domain and the forces and
dynamics of the environment when making a decision.
• A decision maker needs to identify the organizational culture and the
corporate decision-making processes.
1. Environmental scanning and analysis is the monitoring, scanning, and
interpretation of collected information.
2. Variable Identification is critical, as are the relationships among the
variables.
1. Influence diagrams can facilitate the identification process.
8
2. A cognitive map, can help a decision maker develop a better
understanding of a problem, and variable interactions.
Identification of the Problem and Environmental Analysis
3. Predictive analytics (forecasting) is essential for constructing and
manipulating models because the results of an implemented decision occur in
the future.
• There is no point in running a what-if (sensitivity) analysis on the past because
decisions made then have no impact on the future.
• Online commerce and communication has created an immense need for
forecasting and an abundance of available information for performing it.
• These activities occur quickly, yet information about such purchases is
gathered and should be analyzed to produce forecasts.
• Forecasting models use product life-cycle needs and information about the
marketplace to analyze the situation.
9
Model Categories
• The following table classifies decision models into seven groups and lists
several representative techniques for each category.
• Each technique can be applied to a static or a dynamic model, which can be
constructed under assumed environments of certainty, uncertainty, or risk.
10
Model Categories (cont.)
• To expedite model construction, we can use special decision analysis systems
that have modeling languages and capabilities embedded in them.
• These include spreadsheets, data mining systems, online analytic processing
(OLAP) systems, and modeling languages.
• Model Management: Models must be managed to maintain integrity, and
applicability. This is done with the aid of model-based management systems,
which are analogous to database management systems (DBMS).
• Knowledge-based Modeling DSS: use quantitative models, whereas expert
systems use qualitative, knowledge-based models in their applications.
11
Current Trends in Modeling
• One trend in modeling involves the development of model libraries and
solution technique libraries.
• There is a clear trend toward developing and using cloud-based tools and
software to run software to perform modeling, optimization, simulation, etc.
• With management models, the amount of data and model sizes is large,
necessitating data warehouses and parallel computing for solutions.
• There is a trend toward making analytics models transparent to decision
makers, and using influence diagrams (a model of a model to help in analysis).
• Many decision makers accustomed to slicing and dicing data cubes are now
using OLAP systems that access data warehouses.
12
8.3 Structure of Mathematical Models for
Decision Support
•
Components of Decision Support Mathematical Models
•
Examples of Components of Models
•
The Structure of Mathematical Models
13
Components of Decision Support Mathematical Models
• Quantitative models are made up of four basic components: result variables,
decision variables, uncontrollable variables, and intermediate result variables.
• Mathematical relationships link these components together.
• In non-quantitative models, the relationships are symbolic or qualitative. The
results of decisions are determined based on decisions made, uncontrollable
variable, and relationships among variables.
• The modeling process involves identifying the variables and relationships.
Solving a model determines the values of these and the result variable(s).
14
Components of Decision Support Mathematical Models
• Result/Outcome/Output Variables: reflect level of effectiveness of a system.
• Decision Variables: Decision variables describe alternative courses of action.
The decision maker controls the decision variables.
• Uncontrollable Variables/Parameters: fixed/varying factors that affect the
result variables but are not under the decision maker control.
• Intermediate Result Variables: reflect intermediate outcomes in models.
15
Components of Decision Support Mathematical
Models Examples
16
The Structure of Mathematical Models
• Components of a quantitative model are linked by mathematical expressions.
• A very simple financial model is:
• Another financial model is the simple present-value cash flow model.
• It is possible to determine the present value of a payment of $100,000 to be
made 5 years from today, at a 10% interest rate, as follows:
17
8.4 Certainty, Uncertainty, and Risk
18
•
Decision Making under Certainty
•
Decision Making under Uncertainty
•
Decision Making under Risk (Risk Analysis)
Decision Making under Certainty
• In decision making under certainty, complete knowledge is available so
decision maker know the outcome of each course of action.
• This is done with structured problems and short time horizons (up to 1 year).
• Outcomes are not 100% known, but this assumption simplifies the model.
• The decision maker is viewed as a perfect predictor of the future because it is
assumed that there is only one outcome for each alternative.
• Certainty models are easy to develop and solve, and yield optimal solutions.
• Financial models are constructed under assumed certainty.
19
Decision Making under Uncertainty
• Decision maker considers situation where several outcomes are possible for
each course of action.
• In contrast to the risk situation, the decision maker does not know, or cannot
estimate, the probability of occurrence of the possible outcomes.
• Modeling such situations involves assessment of the decision maker’s attitude
toward risk.
• Instead of dealing with uncertainty, manager’s sometimes attempt to obtain
more information so that the problem can be treated under certainty.
• If more information is not available, the problem must be treated under a
condition of uncertainty, which is less definitive than the other categories.
20
Decision Making under Risk (Risk Analysis)
• Risk analysis is a decision-making method that analyzes risk associated with
alternatives, each with a given probability of occurrence.
• The probabilities that the given outcomes will occur are assumed to be known
or can be estimated. Under these assumptions, the decision maker can assess
the degree of risk associated with each alternative (calculated risk).
• Risk analysis can be performed by calculating the expected value of each
alternative and selecting the one with the best expected value.
21
8.6 Mathematical Programming
Optimization
•
Overview
•
Linear Programming Model
•
Implementation
•
Modeling in LP: An Example
22
Overview
• Mathematical programming are tools that helps decision makers allocate scarce
resources among competing activities to optimize a measurable goal.
• Linear programming (LP) is the best-known technique in a family of optimization
tools called mathematical programming.
• In LP, all variable relationships are linear. Applications include supply chain
management, product decisions, etc.
LP allocation problems usually display the following characteristics:
o Limited quantity of resources, most are used in product/service production.
o Two or more ways resources can be used. Each is called a solution/program.
o Each activity where resources are used, yields a return in terms of stated goal.
23
Linear Programming Model
• The LP allocation model is based on the following economic assumptions:
o Returns from allocations are independent and measured by a common unit
o The total return is the sum of the returns yielded by the different activities.
o All data are known with certainty, and resources are used economically
• Allocation problems have a large number of possible solutions. Depending on the
assumptions, the number of solutions can be either infinite or finite.
• Different solutions yield different rewards. The solution with highest degree of
goal attainment is called optimal solution, and found by a special algorithm
24
Linear Programming Model (cont.)
• Every LP model is composed of:
o Decision variables: Unknown values that are being searched for
o Objective Function: A linear mathematical function that relates the decision
variables to the goal, measures goal attainment, and is to be optimized
o Coefficients: indicate contribution to objective of one unit of a decision variable
o Constraint: Linear (in)equalities that limit resources
o Capacities: Describe upper and lower limits on the constraints and variables
o Input/output & Coefficients: Indicate resource utilization for a decision variable
25
Implementation
• Implement the model in “standard form”, where constraints are written with
decision variables on the left and a number on the right.
• Alternatively, use spreadsheet to calculate the model in a less rigid manner.
• LP models can be specified directly in a number of user-friendly modeling
systems. Models are specified in the same way they are defined algebraically.
• Optimization models can be solved by mathematical programming methods:
o Assignment & Network models for planning and scheduling
o Dynamic, Goal, Linear, Nonlinear and Integer programming
o Investment & Replacement
26
o Simple inventory models & Transportation
Modeling in LP: An Example
•
MBI Corporation, which manufactures special-purpose computers, needs to make a
decision: How many computers should it produce next month at the Boston plant?
•
MBI is considering two types of computers:
o CC-7, which requires 300 days of labor and $10,000 in materials, &
o CC-8, which requires 500 days of labor and $15,000 in materials.
•
The profit contribution of each CC-7 is $8,000, and of each CC-8 is $12,000.
•
The plant has a capacity of 200,000 working days per month, and the material budget is $8
million per month.
•
Marketing requires that at least 100 units of the CC-7 and at least 200 units of the CC-8 be
produced each month.
•
Problem: Maximize the company’s profits by determining how many units of the CC-7
and how many units of the CC-8 should be produced each month.
27
Modeling in LP: An Example (cont.)
• The problem is to find the values of the decision variables X1, X2, such that the value of
the result variable Z is maximized, subject to a set of linear constraints that express the
technology, market conditions, and other uncontrollable variables.
• The mathematical relationships are all linear equations and inequalities.
28
Modeling in LP: An Example (cont.)
• Theoretically, any allocation problem of this type has an infinite number of possible solutions.
• Using special mathematical procedures, the LP approach applies a unique computerized
search procedure that finds the best (optimal) solution/s (ex. maximizes total profit) in a
matter of seconds.
• Excel ‘add-in Solver’ is used to obtain an optimal (best)
solution to this problem. Open spreadsheet
DS498_week7-Ch8d.xlsx
1. Activate ‘Solver’ Under the Data tab and on the
Analysis ribbon.
29
If it is not there, you should be able to enable it by
going to File -> Excel’s Options Menu and selecting
Add-ins.
Modeling in LP: An Example (cont.)
2. Enter these data directly into an Excel spreadsheet.
3. Identify the goal (by setting Target Cell equal to Max).
4. Identify decision variables (by setting By Changing Cells).
5. Identify constraints on labor capacity, budget, and the desired minimum production
of the two products X1 and X2.
6. Clicking on the Solver Add-in opens a dialog box,
o Specify the cells or ranges that define the objective function cell, decision/changing
variables (cells), and the constraints.
o Select the solution method (usually Simplex LP)
o solve the problem.
7. Next, we select all three reports—Answer, Sensitivity, and Limits (optimal solution of X1
= 333.33, X2 = 200, Profit = $5,066,667)
30
8.7 Multiple Goals, Sensitivity Analysis,
What-If Analysis, and Goal Seeking
•
Multiple Goals
•
Sensitivity Analysis
•
Types of Sensitivity Analysis
•
What-If Analysis
•
What-If Analysis Example
•
Goal Seeking
•
Goal Seeking Example
31
Multiple Goals
• Today’s management systems are complex, and managers want to attain
simultaneous goals, some of which may conflict.
• Transform a multiple-goal problem into a single-measure-of effectiveness
problem before comparing the effects of the solutions.
• Certain difficulties may arise when analyzing multiple goals:
o It is difficult to obtain the organization’s goals explicitly
o Goals are viewed differently at various levels of the organization
o Goals and their importance change in response to the organization
o Complex problems are solved by decision makers with different agendas
32
Sensitivity Analysis
• Sensitivity analysis assesses impact of input data changes on proposed
solution.
• Sensitivity analysis allows for:
o Adaptation to conditions of different decision-making situations
o Provides a better understanding of the model
o Permits the input of data to increase model confidence.
33
Sensitivity Analysis (cont.)
Sensitivity analysis tests relationships such as the following:
• Impact of parameter change, and decision variables on outcome variable(s)
• The effect of uncertainty in estimating external variables
• The effect of different dependent interactions among variables
• The robustness of decisions under changing conditions
Sensitivity analyses are used for:
• Revising models to eliminate too-large sensitivities
• Detailing variables and obtaining estimates of sensitive external variables
• Altering a real-world system to reduce actual sensitivities
34
Types of Sensitivity Analysis
• The two types of sensitivity analyses are automatic and trial and error.
Automatic Sensitivity Analysis:
• This is performed in standard quantitative model implementations such as LP.
• It is usually limited to one change at a time, and only for certain variables.
• It is powerful because of its ability to establish ranges and limits very fast
Trial-and-error Sensitivity Analysis:
• Impact of changes in variable(s) is determined by trial-and-error approach
• When changes are repeated, better and better solutions may be discovered.
• Such experimentation has two approaches: what-if analysis and goal seeking.
35
What-If Analysis
• What-if analysis is structured as: What will happen to the solution if an input
variable, assumption, or parameter value is changed?
o Total inventory cost if the carrying inventories cost increases by 10%?
o Market share if the advertising budget increases by 5%?
• With the appropriate user interface, managers can ask a computer model
these types of questions and get immediate answers.
• Performs multiple cases and change the percentage, or other data as needed.
• What-if analysis is common in many decision systems. Users are given the
opportunity to change their answers to the system’s questions, and a revised
recommendation is found.
36
What-If Analysis Example
A what-if query for a cash flow problem: the user changes the cells containing
the initial sales (from 100 to 120) and the sales growth rate (from 3% to 4% per
quarter), the program immediately re-computes the value of the annual net
profit cell (from $127 to $182) .
37
Goal Seeking
• Goal seeking calculates the values of the inputs necessary to achieve a desired
level of an output (goal). The following are some examples:
o Annual R&D budget is needed for an annual growth rate of 15% by 2018?
o How many nurses needed to reduce the average waiting time of a patient in
the emergency room to less than 10 minutes?
• Computing A Break-even Point By Using Goal Seeking:
o Determining the value of the decision variables that generate zero profit.
o Some modeling software packages can directly compute break-even points,
which is an important application of goal seeking.
o Sensitivity analysis as the prewritten routines present a limited opportunity for
asking what-if questions.
38
Goal Seeking
• In a financial planning model, the internal
rate of return (IRR) is the interest rate that
produces a net present value (NPV) of
zero.
• Given a stream of annual returns in
Column E, we can compute the NPV of
planned investment through goal-seeking.
• An NPV equal to zero determines the IRR
of this cash flow, including the investment.
We set the NPV cell to 0 by changing the
interest rate cell.
• The answer is 38.77059%.
39
8.8 Decision Analysis with Decision Tables
& Decision Trees
•
•
•
Decision Tables
Decision Tables Example
Decision Trees
40
Decision Tables
• Decision tables organize information in systematic, tabular form for analysis.
• Treating Uncertainty: Several methods are available for handling uncertainty.
o Optimistic approach: assumes and selects best outcomes for alternatives
o Pessimistic approach: assumes worst outcome for alternatives; selects the best
o Another approach simply assumes that all states of nature are equally possible.
• When possible, analysts should attempt to gather information to treat the
problem under assumed certainty.
• Treating Risk: The most common method for solving this risk analysis problem
is to select the alternative with the greatest expected value.
41
Decision Tables Example
• An investor estimates: solid growth (50%), stagnation (30%), and inflation (20%)
• Expected value is computed by multiplying result probabilities and adding them
Bond investment yields an expected return of 12(0.5) + 6(0.3) + 3(0.2) = 8.4%
• This approach can sometimes be a dangerous strategy such as a financial
advisor presents a $1,000 investment with 0.9999 chance to double your money,
and 0.0001 chance you’ll lose $500,000.
• The expected value of this investment is $949.80
• The potential loss could be catastrophic for any investor
42
Decision Trees
• Decision trees are alternative representations of a decision table; it shows a
problem’s relationship graphically and handles complex situations compactly.
• TreeAge Pro & PrecisionTree are systems that show decision trees in practice.
• You can apply mathematical programming to decision-making situations under
risk. These include simulation, certainty factors, and fuzzy logic.
• A simplified investment case of multiple goals is shown in the table. The three
goals are yield, safety, and liquidity. This situation is under assumed certainty.
43
8.9 Introduction to Simulation
•
•
•
•
•
•
•
Major Characteristics of Simulation
Advantages of Simulation
Disadvantages of Simulation
The Methodology of Simulation
Simulation Types
Monte Carlo Simulation
Discrete Event Simulation
44
Major Characteristics of Simulation
• Simulation involves building a model of reality to the extent practical.
• Simulation models may suffer from fewer assumptions about the decision
situation as compared to other prescriptive analytic models.
• Simulation is a technique for conducting experiments. Therefore, it involves
testing specific values of the decision or uncontrollable variables in the model
and observing the impact on the output variables.
• Simulation is used only when a problem is too complex to be treated using
numerical optimization techniques.
• Complexity in this situation means either that the problem cannot be
formulated for optimization, that the formulation is too large, that there are
too many interactions among the variables.
45
Advantages of Simulation
Simulation is used in decision support modeling for the following reasons:
• The theory is straightforward, and model is built from manager’s perspective.
• Time compression is attained quickly to give idea of policies’ long-term effects.
• Descriptive rather than normative, allowing managers to ask what-if
questions, and use a trial-and-error approach with less expense and risk.
• Requires intimate knowledge; model builder constantly interact with manager.
• Can handle a variety of problem types and higher-level managerial functions.
• Produces performance measures, and includes real complexities of problems.
• Can readily handle relatively unstructured problems.
46
Disadvantages of Simulation
• An optimal solution cannot be guaranteed, but relatively good ones are
generally found.
• Simulation model construction can be a slow and costly process, although
newer modeling systems are easier to use than ever.
• Solutions and inferences from a simulation study are usually not transferable
to other problems because the model incorporates unique problem factors.
• Simulation is sometimes so easy to explain to managers that analytic methods
are often overlooked.
• Simulation software sometimes requires special skills because of the
complexity of the formal solution method.
47
The Methodology of Simulation
Simulation involves setting up a model of a real system through the steps:
• Define the problem: Examine problem, and specify need for simulation
• Construct model: Determine variables, relationships, and gather data.
• Test and validate model: Ensure model properly represents studied system.
• Design experiment: There are two conflicting objectives: accuracy and cost.
• Conduct experiment: can involve issues like number generation.
• Evaluate results: Statistical tools/sensitivity analyses used to interpret results.
• Implement results: Managerial involvement leads to implementation success.
48
The Methodology of Simulation
49
Simulation Types
• Simulation model consists of relationships that present the real-world
operations. Simulation results depend on the set of parameters given as inputs.
• There are various simulation paradigms such as Monte Carlo simulation,
discrete event, agent based, or system dynamics.
• The level of abstraction in a problem can determine simulation technique.
• Discrete events and agent based models are used for low levels of abstraction.
• They consider individual elements such as people in the simulation models,
whereas systems dynamics is more appropriate for aggregate analysis.
• Here we introduce the major types of simulation: probabilistic simulation, timedependent and time-independent simulation, and visual simulation.
50
Simulation Types
• Probabilistic Simulation: One or more independent variables are probabilistic.
They follow probability distributions, which can be discrete or continuous:
o Discrete involves situations with limited event numbers and finite values.
o Continuous distributions are situations with unlimited numbers of possible
events that follow density functions, such as the normal distribution.
• Time-dependent Versus Time-independent Simulation:
o Time-independent refers to situations where time of event occurrence is
unimportant. For example, we may know that the demand for a product is 3
units/day, but do not care when during the day the item is demanded.
o However, in waiting-line problems applicable to e-commerce, it is important to
know the precise time of arrival. This is a time-dependent situation.
51
Monte Carlo Simulation
• In business decision problems, we employ probabilistic simulations. The
Monte Carlo simulation is commonly used.
• This method begins with building a model of the decision problem without
having to consider the uncertainty of any variables.
• Then we recognize that certain variables are uncertain or follow an estimated
probability distribution. This estimation is based on analysis of past data.
• Then we begin running sampling experiments. This consists of generating
random values of uncertain parameters and then computing values of the
variables that are impacted by such parameters or variables.
• We then analyze the behavior of these performance variables by examining
their statistical distributions.
52
Discrete Event Simulation
• Discrete event simulation refers to building a model of a system where the
interaction between different entities is studied.
• An example of this is modeling the customers arriving at various rates and the
server serving at various rates, we can estimate the average system
performance, waiting time, number of waiting customers, etc. Such systems
are viewed as collections of customers, queues, and servers.
• There are thousands of documented applications of discrete event simulation
models in engineering, business, and so on.
• Tools for building discrete event simulation models have been around for a
long time, but these have evolved to take advantage of developments in
graphical capabilities for building and understanding the results of such
simulation models.
53
8.10 Visual Interactive
Simulation
•
•
54
Visual Interactive Simulation
Visual Interactive Models and DSS
Visual Interactive Simulation
• Visual interactive simulation (VIS), visual interactive modeling (VIM) and visual
interactive problem solving, is a simulation method that lets decision makers see
what a model is doing, how it interacts with made decisions.
• Users employ knowledge to try different decision strategies while interacting with
the model. Decision makers can contribute to model validation.
• VIS uses animated computer graphic displays to present the impact of different
managerial decisions. It differs from regular graphics in that the user can adjust
the decision-making process and see results of the intervention.
• VIS can represent static or dynamic systems. Static models display a visual image
of the result of one decision alternative at a time. Dynamic models display
evolving systems over time. The evolution is represented by animation.
55
Visual Interactive Models (VIM) and DSS
• VIM in DSS has been used in several operations management decisions.
• The method consists of priming a visual interactive model of a company with
its current status.
• Waiting-line management is a good example of VIM. Such a DSS usually
computes measures of performance for the various decision alternatives.
• Complex waiting-line problems require simulation. VIM can display the size of
the waiting line as it changes during the simulation runs and can graphically
present the answers to what-if questions regarding changes in input variables.
• The VIM approach can be used with AI. Integration of the two techniques adds
several capabilities that range from the ability to build systems graphically to
learning about the dynamics of the system.
56
6.2 Introduction to Deep Learning
• Introduction to Deep Learning
• Classic Machine-Learning vs Deep Learning
Introduction to Deep Learning
• Deep learning is among the latest trends in AI that come with great expectations.
• The initial idea of deep learning goes back to the late 1980s.
• Goal: mimic the thought process of humans—using mathematical algorithms to learn from data pretty
much the same way that humans learn (similar to those of the other machine-leaning methods).
• It has added the ability to automatically acquire the features required to accomplish highly complex and
unstructured tasks (e.g. image recognition) to the classic machine-learning methods that contribute to the
superior system performance.
• The recent emergence and popularity of deep learning can largely be attributed to very large data sets and
rapidly advancing commuting infrastructures.
• Many deep learning applications have promised to make our life easier.
 E.g., Google Home, Amazon’s Alexa, Google Translate, …)
Introduction to Deep Learning
• Deep learning is an extension of neural networks with the idea that deep
learning is able to deal with more complicated tasks with a higher level of
sophistication.
• Neural networks are extended by employing many layers of connected
neurons along with much larger data sets to automatically characterized
variables and solve the problems.
• The initial idea of deep learning had to wait more than two decades until
some advanced computational and technological infrastructure emerged,
because of:
1. Very high computational requirement.
2. The need for very large data sets.
Introduction to Deep Learning
Placement of Deep Learning within the Overarching AI-Based Learning Methods
• Deep learning is categorized as part of the representation learning within the AI learning
family of methods
• Representation learning focus on learning and discovering features by the system in
addition to discovering the mapping from those features to the output/target.
Classic Machine-Learning vs Deep Learning
• In Knowledge-based systems and
classic machine-learning methods,
features (i.e., the representation)
are created manually by data
scientists to achieve the desired
output.
• Deep learning enables the
computer to derive some complex
features from simple concepts that
would be very effort intensive to be
discovered by humans manually.
6.3 Basics of “Shallow” Neural Networks
• Artificial Neural Networks (ANN)
• Elements of an Artificial Neural Network
• Common Transfer Functions in Neural Networks
• The human brain has a set of billions of interconnected neurons that facilitate our thinking,
learning, and understanding of the world around us.
• Artificial neural networks emulate the way the human brain works.
• The basic processing unit is a neuron. Multiple neurons are grouped into layers and linked
together.
VS
neurons
A Biological Neural Network: Two Interconnected
Cells/Neurons.
ANN with single neuron, single inputs and outputs
• The basic processing unit is a neuron (processing element
– PE).
• PE: perform a set of predefined mathematical operations
on the numerical values coming from the input or from
the other neuron outputs to create and push out its own
outputs.
PE
PE
PE
• A neuron can have more than a single input p, each of
the individual input values would have its own adjustable
weight w.
• In a neural network, knowledge is stored in the weight
associated with the connections between neurons.
Typical Neural Network with Three Layers and Eight
Neurons.
• Multiple neurons are grouped into layers and linked
together.
Ele me nts of an Arti fici al N eu ral N etw ork
• Processing element (PE)
• Network architecture
• Hidden layers
• Parallel processing
• Network information processing
• Inputs
• Outputs
• Connection weights
• Summation function
• Transfer Function
Elements of an Artificial Neural Network
Summation Function for a Single
Neuron/PE (a), and
Several Neurons/PEs (b)
Neural Network with
One Hidden Layer
• Various types of transfer functions are commonly used in the design of neural
networks.
• Common Transfer Function types (Linear function, Sigmoid (log) function [0 1]
and Tangent Hyperbolic function [-1 1]).
• Example of ANN Transfer Function (sigmoid-type activation function)
• The selection of proper transfer functions for a
network requires a broad knowledge of neural
networks ( e.g. characteristics of the data as well as
the specific purpose for which the network is
created).
• There are some guidelines for choosing the
appropriate transfer function especially for the
neurons located at the output layer of the network.
• E.g., if the nature of the output for a model is binary,
it is advised to use Sigmoid transfer functions at the
output layer so that it produces an output between 0
and 1.
some of the most common transfer functions
and their corresponding operations
6.4 Process of Developing Neural Network–Based Systems
• Development Process of an ANN Model
• Learning Process in ANN
• Backpropagation Learning for ANN
• Overfitting in ANN
• Developing neural network–based systems requires a step-by-step process.
• A supervised learning process.
• The learning process is inductive; that is,
connection weights are derived from existing
cases.
• The usual process of learning involves three
tasks:
 Compute temporary outputs.
 Compare outputs with desired targets.
 Adjust the weights and repeat the
process.
Supervised Learning Process of an ANN.
• Backpropagation is the most popular supervised learning paradigm for ANN.
Backpropagation of Error for a Single Neuron
Backpropagation Learning for ANN
The learning algorithm procedure:
1. Initialize weights with random values and set other
parameters.
2. Read in the input vector and the desired output.
3. Compute the actual output via the calculations, working
forward through the layers.
4. Compute the error.
5. Change the weights by working backward from the output
layer through the hidden layers.
• Occurs when neural networks
are trained for a large number
of iterations with relatively
small data sets.
• To prevent overfitting, the
training process is controlled by
an assessment process using a
separate validation data set.
6.5 ILLUMINATING THE BLACK BOX OF ANN
Overfitting in ANN—Gradually Changing Error Rates in
the Training and Validation Data Sets As the Number of
Iterations Increases.
• Sensitivity Analysis on ANN Models
•
•
•
•
ANNs are known as black-box models.
 But, “how the model does what it does?”
ANNs lack of explanation/transparency -> black-box syndrome!
To shed light into the black-box syndrome sensitivity analysis is applied.
Sensitivity analysis:
1. Preformed on a trained ANN
2. Perturbed the inputs to the network systematically within the allowable
value ranges.
3. The corresponding change in the output is recorded for each and every
input variable.
4. The relative importance of input variables are illustrated in the result.
• Sensitivity analysis extract the cause-and-effect relationships
among the inputs and the outputs of a trained neural network
model.
•6.6 Deep
Deep Neural
Networks
Neural
Networks
• Feedforward Multilayer Perceptron (MLP)
•
Most neural network applications involved network architectures with only a few hidden
layers and a limited number of neurons in each layer.
•
Deep neural networks broke the generally accepted notion of “no more than two hidden
layers are needed to formulate complex prediction problems.”
•
They promote increasing the hidden layer to arbitrarily large numbers to better represent
the complexity in the data set.
•
Different types of deep networks involve various modifications to the architecture of
standard neural networks.
 Typically equipped with distinct capabilities of dealing with particular data types for
advanced purposes (e.g. image or text processing).
• MLP deep networks (a.k.a deep feedforward networks) are the most general type of deep
networks.
• MLP Consists of an input layer, an output layer, and a number of hidden layers.
• The nodes in one layer are connected to the nodes in the next layer.
• Each node at the input layer typically represents a single attribute that may affect the prediction.
• The flow of information is always forwarding and no feedback connections, hence it is called “called
feedforward network”.
More Hidden Layers versus More Neurons?
 it is still an open research question, practically using more layers in a network seems to be more and computationally
more efficient than using many neurons in a few layers.
The First Three Layers in a Typical MLP Network.
Deep COMPUTER FRAMEWORKS FOR IMPLEMENTATION
•6.7
Frameworks
OF DEEP LEARNING
• Example DL Applications
• Deep learning implementation frameworks (open-source) include:
 Torch: is a scientific computing framework for implementing machine-learning algorithms
using GPUs.
 Caffe: The deep learning libraries are written in the C++ programming language, everything is
done using text files instead of code.
 TensorFlow: a popular deep learning framework, It was originally developed by the Google
Brain Group.
 Theano: one of the first deep learning frameworks
 Keras: functions as a high-level application programming interface (API) and is able to run on
top of various deep learning frameworks including Theano and TensorFlow.
Source: https://www.mygreatlearning.com/blog/what-is-deep-learning/
•6.8 Conceptual
Cognitive ComputingFramework for Cognitive Computing
• How Does Cognitive Computing Work?
• Cognitive Computing and AI
• Typical use cases for cognitive computing
• Cognitive analytics and Search
• IBM Watson
• Cognitive computing makes a new class of problems computable.
• It address highly complex situations that are characterized by ambiguity
and uncertainty.
• Handles the kinds of problems that are thought to be solvable by human
ingenuity and creativity.
• Computing system offers a synthesis not just of information sources but
also of influences, contexts, and insights that help users understand their
problems.
•
To provide the best possible
answers to a given question or
problem, cognitive computing:

finds and synthesizes data from
various information sources,

And weighs the context and
conflicting evidence inherent in
the data.

And suggest an answer that is
“best” rather than “right.”
a general framework for cognitive computing
where data and AI technologies are used to solve
• Cognitive computing works much like a human thought process, reasoning
mechanism, and cognitive system.
• It includes self-learning technologies that use data mining, pattern recognition, deep
learning, and NLP to mimic the way the human brain works.
• Cognitive systems may draw on multiple sources of vast amounts of information,
including structured and unstructured data and visual, auditory, or sensor data solve
the types of problems that humans are typically tasked.
• Over time, cognitive systems are able to refine the way in which they learn and
recognize patterns and the way they process data to become capable of anticipating
new problems and modelling and proposing possible solutions.
H o w D oe s C og nitiv e C om pu ting W ork ?
The key attributes of cognitive computing capabilities:
 Adaptability: be flexible enough to learn as information changes and goals
evolve.
 Interactivity: Users must be able to interact with cognitive machines and define
their needs as those needs change.
 Iterative and stateful: ability to maintaining information about similar situations
that have previously occurred.
 Contextual: must understand, identify, and mine contextual data, such as syntax,
time, location, domain, requirements, and a specific user’s profile, tasks, or goals.
Cognitive Computing and AI
• Development of smart and adaptive search engines.
• Effective use of natural language processing.
• Speech recognition.
• Language translation.
• Context-based sentiment analysis.
• Face recognition and facial emotion detection.
• Risk assessment and mitigation.
• Fraud detection and mitigation.
• Behavioral assessment and recommendations.
Typical use cases for cognitive computing
• Cognitive analytics is a term that refers to cognitive computing–branded
technology platforms.

E.g., IBM Watson specialize in the processing and analysis of large unstructured data sets.
• The benefit of utilizing cognitive analytics over traditional Big Data analytics
tools is that for cognitive analytics such data sets do not need to be
pretagged.
• Cognitive analytics systems can use machine learning to adapt to different
contexts with minimal human supervision.
 These systems can be equipped with a chatbot or search assistant that understands queries,
explains data insights, and interacts with humans in human languages.
• Searching for information is a tedious task.
• Cognitive search is the new generation of search method that uses AI (e.g.,
advanced indexing, NLP, and machine learning) to return results that are
much more relevant to the user than traditional search methods.
• It creates searchable information out of non-searchable content by
leveraging cognitive computing algorithms to create an indexing platform.
•
Cognitive search proposes the next generation of search tailored for use in
enterprises.
Cognitive search is different from traditional
search because, according to Gualtieri (2017),
it:




Can handle a variety of data types.
Can contextualize the search space.
Employ advanced AI technologies.
Enable developers to build enterprisespecific search applications.
The progressive evolution of search methods.
•
IBM Watson is perhaps the smartest computer system built to date. It has coined and
popularized the term cognitive computing.
•
It is an extraordinary computer system—a novel combination of advanced hardware
and software—designed to answer questions posed in natural human language.
•
IBM Watson beat the best of men (the two most winning competitors) at the quiz game
Jeopardy!, showcasing the ability of commuters to do tasks that are designed for human
intelligence.
• Watson and systems like it are now in use in many application areas including:
 Healthcare, finance, security, retail, education, government and research.
• DeepQA is the system behind Watson, which is a massively parallel, text mining–
focused, probabilistic evidence–based computational architecture.
• Goal: to bring their strengths to bear and contribute to improvements in accuracy,
confidence, and speed.
Principles in DeepQA
 Massive parallelism.
 Many experts.
 Pervasive confidence estimation.
 Integration of shallow and deep knowledge.
A High-Level Depiction of DeepQA Architecture
College of Computing and Informatics
Assignment 2
Deadline: 05/05/2024 @ 23:59
[Total Mark for this Assignment is 8]
Student Details:
Name: ###
ID: ###
CRN: ###
Instructions:
• You must submit two separate copies (one Word file and one PDF file) using the Assignment Template on
Blackboard via the allocated folder. These files must not be in compressed format.
• It is your responsibility to check and make sure that you have uploaded both the correct files.
• Zero mark will be given if you try to bypass the SafeAssign (e.g. misspell words, remove spaces between
words, hide characters, use different character sets, convert text into image or languages other than English
or any kind of manipulation).
• Email submission will not be accepted.
• You are advised to make your work clear and well-presented. This includes filling your information on the cover
page.
• You must use this template, failing which will result in zero mark.
• You MUST show all your work, and text must not be converted into an image, unless specified otherwise by
the question.
• Late submission will result in ZERO mark.
• The work should be your own, copying from students or other resources will result in ZERO mark.
• Use Times New Roman font for all your answers.
Restricted – ‫مقيد‬
Question One
Pg. 01
Learning
Outcome(CLO2):
Instructors:
Describe
advanced
Business
Intelligence,
Business
Analytics, Data
Visualization, and
Dashboards.
Restricted – ‫مقيد‬
Question One
2 Marks
Define data visualization and discuss its significance in data analysis. Provide
examples of different types of charts and graphs and explain when each type is
most appropriate to use.
Question Two
Pg. 02
Learning
Outcome(CLO1):
Question Two
2 Marks
Discuss the differences between …