Credit-Card-Default-Prediction

Problem Description

This project is aimed at predicting the case of customers default payments in Taiwan. From the perspective of risk management, the result of predictive accuracy of the estimated probability of default will be more valuable than the binary result of classification - credible or not credible clients. We can use the K-S chart to evaluate which customers will default on their credit card payments

Steps Performed In This ML(Supervised) Project

Handling dataset with the fundamental steps to unvail the factors :

Importing Libraries And Loading The Datasets

Overview Of The Datasets

Reading & Inspection Of First Dataset

Further analysing both the datasets

Data Wrangling And Processing

Exploratory Data Analysis

Key Findings From EDA

Feature Engineering

Feature Selection

Multicollinearity

Dependent Variable Transformation

Scaling Numberical Features

Dummification

ML Model

Train-Test Split

Model Training And Prediction

1.Logistic Regression

2.Support Vector Classifier(SVC)

3.Random Forest Classifier

4.Xgboost Classifier

Feature Importance

HyperParameter Tuning

Feature Importance of Best performing Model

Cross Validating for Hyperparameter Tuned Best Performing model

Key Findings from Machine Learning