This Python prject describes the implementation and data visualization of 6 supervised machine learning techniques implemented on the kaggle dataset of credit card defaulters.
As the data is huge in terms of calculations i have used google colab and so first few steps are dedicated for setting up cloud environment.
The main scope for this project is to predict the occurence of credit card defaulter based on a customers previous history. The data provided in the csv file are in huge dimensions and the data used here is a PCA of multidimensions data reducing the dimensions so that we can handle with limited computational resources.
The techniques compared in this file are namely: 1)SVM 2)Decision Tree 3)Random Forest 4)Logistic Regression 5)K nearest neighbours 6) Ensemble classifier using decision trees.