Build machine learning models to improve the efficacy of fraudulent transaction alerts. The data comes from Vesta's real-world e-commerce transactions and contains a wide range of features from device type to product features.

This repository contains code for PCA (Principal Component Analysis with fixed number of components) that reduces the number of dimensions, PCA with Scree plot (finding number of optimal components that explains maximum variance) in Fraud data set from Kaggle competition that contains more than 500 variables.