Introduction

As a key component of the Predictive Modeling$/$Analytics course $($MGSC $5125),$ students are tasked with completing a project that not only demonstrates their understanding of the course material but also challenges them to apply and expand upon these concepts in a practical context. This project will constitute $40\%$ of the final grade. The guidelines provided below are aimed to guide the students through the project process.

Project Option:

Practical Predictive Modeling Project

Objective:

To demonstrate the ability to apply predictive modeling techniques to a real$-$world dataset and extract meaningful insights, incorporating predictive, descriptive, and prescriptive analytics.:

Requirements:

Data Selection: Choose a dataset with more than $5,000$ data points from reputable sources such as the UCI Machine Learning Repository, Kaggle, or similar. The dataset should be relevant to the theme of predictive analytics. No private datasets are allowed due to the delay in the legal process of filing a nondisclosure agreement with the university. Here is a list of public repositories of data that you can use for your projects. You need to select one of the following datasets or any other public dataset that match one of the above themes that you selected. You can also use built in data sets in the R software.

Analysis Methodology: Implement methods from each of the three analytics domains:

Predictive Analytics: Techniques like Logistic Regression, Random Forests, or Neural Networks to forecast future trends or behaviors.

Descriptive Analytics: Use methods such as Data Visualization, Summary Statistics, or Clustering to understand past and current trends.

Prescriptive Analytics: Apply Optimization, Simulation, or Decision Analysis to recommend actions for optimal outcomes.

Tools for Analysis and Visualization: You may use R$,$ Python for analysis, and for visualization, tools such as Excel, Tableau, R$,$ and Python are recommended.

Report Structure: Your report $(15-20$ pages$)$ should include:

$$ Introduction: Overview of the dataset and the chosen methods across the three analytics domains.

$$ Data Preparation: Describe preprocessing steps $($e$.$g$.,$ cleaning, normalization$).$

$$ Method Application: Detailed explanation of how each method was applied within the predictive, descriptive, and prescriptive frameworks.

$$ Results & Insights: Present visualizations and interpretations of the outcomes.

$$ Conclusion: Summarize the key findings and their business implications.

References: Cite all sources and tools utilized.