Project Intro/Objective : The purpose of this project is to develop an strategy to predict future credit card default payments based on data on existing customers, with the goal of enhancing business revenue and for better risk management. Here, we are using Machine Learning Techniques and advanced analytics to get to as accurate of predictions as possible. The hope is this will help the business be better at revenue generation and better risk management for this high risk business operation.

Methods Uses. Logistic Regression, Inferential Statistics, Machine Learning, Predictive Modeling, Data Visualization

Technologies Python Jupyter Notebooks Pandas, NumPy, scikit-learn Matplotlib, Seaborn, Plotly SQL (PostgreSQL/MySQL) Git/GitHub

Project Description This is a dataset for research that focuses on predicting customer default payments in Taiwan, comparing the accuracy of default probability predictions across six data mining methods. Data Characteristics: Multivariate, Features: 23 (Integer, Real).