Business Question

Objective

Using the flights data from the Unit 3 of this course, develop an interactive analytic project with Quarto and Shiny. This project is an opportunity to demonstrate your ability to handle a complex data analytics project from start to finish. You are encouraged to apply creative thinking and go beyond the basic requirements where possible.

Requirements

• Pick an airline, and assume the role of business analyst at such airline. At your own discretion, you can can focus your analysis on one or more areas; Presume your target audience and their existing view/knowledge; Clearly state the above information at the beginning of the document.
• You may use existing material from your Mid-term projects.
• Perform the following:Data Cleaning and Preprocessing: Perform necessary transformations to prepare the dataset for analysis.Exploratory Data Analysis: Conduct an initial exploration to understand the characteristics and distributions of the data. Use visualizations to identify patterns, trends, and anomalies.Insights and Strategies: Analyze the findings from the exploratory data analysis to develop insights. Formulate strategies for decision-making and potential interventions based on these insights.Predictive Modeling: Choose one or two predictive modeling tasks and apply different algorithms/parameters. Evaluate model performance using relevant metrics.Interactive Elements: Use Shiny components to enrich user experience by presenting data in different combinations of options and allow the user to perform what-if analyses.Recommendation for Downstream: Provide guidelines and recommendations for applying the insights and models in practical scenarios. Suggest further areas of research or additional data that could enhance the understanding and effectiveness of the strategies proposed.

Project Structure

The final project should have the following structure:

• presentation.qmdThe entry point of the project; I’m going to run this fileThis file will first check whether preprocess.R has already been run with expected output fileIf existing and expected, continue to runIf existing and unexpected, stop the program and signal an errorIf missing, run preprocess.R, then continueIt must contain all analyses, literature, documentation, etcThe output must be HTML (not PDF/PPTX, etc)
• preprocess.RTakes the flights data, and transforms it into an adequate form for use within presentation.qmdWrites the result to the folder as data.rdsThis rds file will be read by presentation.qmdDo not include this rds file in your submission
• ../dataContains the three files of the flights dataLives in the parent folder of your projectDo not include this folder in your submission

Consult the following diagram for clarification.

/project │ (your project)├── presentation.qmd ├── preprocess.R └── data.rds (to be generated by `preprocess.R`) /data │ (I will have this ready on my machine)├── flights.csv ├── airlines.csv └── airports.csv

You submission should be a zip file of the contents of /project; It should not contain the /project folder, but only the three files at the top level. If you are from Group 1, your file should be named group01.zip, so forth.

Grading

Grade composition and grading rubric for this project will be published separately.

Presentation

Your group will be allocated 8 – 10 minutes to present your project on April 22nd and 26th; Everyone must speak, ideally on the part of their own contribution;Attendance in both days is required and is a part of your grade.Below is the link for data:- https://we.tl/t-VBpB2P5Xie