Financial-Services-Consumer-Analytics

Overview

Welcome to the Financial Services Consumer Analytics repository! This repository showcases my work for the IT Readiness Boot Camp Data Science with Python Final Exam. The exam tackled a real-world scenario involving consumer dispute data from Company XYZ, a financial services provider. The tasks encompassed data wrangling, exploratory data analysis (EDA), and the application of machine learning techniques to address business problems related to consumer disputes.

Content

This repository is a comprehensive collection of my work, organized into various sections:

1. Data Wrangling

Demonstrates my proficiency in data wrangling techniques, showcasing how I cleaned and refined the consumer dispute data to ensure data quality and accuracy.

2. Exploratory Data Analysis

Provides an immersive EDA of the consumer dispute dataset, going beyond numbers to uncover insights. This section identifies five potential business problems related to consumer disputes, laying the foundation for the machine learning solutions that follow.

3. Machine Learning Models

Presents a showcase of three distinct machine learning models/algorithms, each tailored to address specific business problems. The choice of models is carefully justified based on their suitability for the given tasks.

4. Model Evaluation

Highlights the rigorous evaluation process for each machine learning model. Detailed performance metrics are provided, culminating in the selection of the best-performing model for each business problem.

5. Sentiment Analysis

This section delves into a fascinating journey of identifying a pivotal feature to gauge consumer sentiment. It unravels the sentiment analysis approach employed to predict whether a consumer dispute will lead to a ‘Consumer disputed’ outcome.

How to Use

  1. Clone this repository to your local machine using git clone.
  2. Navigate to the respective lab directories to access the code, notebooks, and documentation for each lab.
  3. Study the notebooks to grasp the intricacies of data preprocessing, analysis, and machine learning techniques applied.
  4. Explore the model evaluation section to understand the rationale behind choosing the best models and their corresponding performance metrics.
  5. Dive into the sentiment analysis section to gain insights into the fascinating world of predicting consumer sentiment.

Acknowledgments

I extend my heartfelt gratitude to the instructors and peers at the IT Readiness Boot Camp for their unwavering support, valuable insights, and guidance throughout this project.

Contact Information

Feel free to connect with me via email or LinkedIn for any inquiries, feedback, or discussions:

Email LinkedIn