ML_Pipeline_For _Freddie-Mac_Mortgage_Loans_PrepaymentRisk

This project aims to predict loan pre-payment likelihood based on various factors such as Equated Monthly Installment (EMI), total payment, interest amount, monthly income, current principal, and whether the person has ever been delinquent in their loan payments. The project is hosted on GitHub and provides a detailed description of the steps involved in building the pipeline. The dataset used in this project is obtained from Freddie Mac’s official portal for home loans and contains 291452 data points and 28 columns or parameters which denote different features of the data. The project involves several steps such as Exploratory Data Analysis (EDA), Data Cleaning, Feature Engineering, and Dimensionality Reduction using Principal Component Analysis (PCA). The project also uses Mutual Information as a feature selection technique to identify the most relevant features in a dataset for building predictive models.