Develop a robust machine learning model to accurately classify whether a new loan borrower is likely to default, thereby aiding ABC Bank in minimizing financial risks associated with loan defaults.

MIT - Applied Data Science Program: Leveraging AI for Effective Decision-Making Certification

This project builds a model to predict if Lending Club loans will be fully paid or charged off. Using completed loan data, it includes credit history and loan grades but excludes FICO scores and rejected loans due to limited data. Methodologies and results are documented for accuracy and fairness.

This project aims to predict loan approval status based on customer behavior and demographic information. By analyzing various factors, we can identify the key determinants of loan approval and improve the decision-making process for financial institutions.

[Project Repo] Bank loan default prediction with machine learning models

This project aims to predict credit risk for individuals applying for loans, classifying whether they will default based on features such as age, income, employment length, loan amount, interest rate, percentage of income, credit length, home ownership, and loan intent.

Decentralised Loan App Running On Local Ehtereum Blockchain

In this project, I analyzed the prosper load data, studied the trends and concluded that monthly income, loan amount and borrower's rate significantly affect the prosper rating and a good predictors of delinquency.

The project aims to develop a predictive model for loan default using the dataset given by Imperial College London. The goal is to analyse the data, understand the factors that contribute to loan defaults, and create a machine learning model that can forecast the likelihood of loan default for future borrowers.

Predicting Loan Defaults using 15+ Features and over 250,000 records

This project demonstrates the implementation of a loan approval system that utilizes MongoDB for distributed data storage and management, and PyMongo for database operations. The project aims to automate the assessment of loan eligibility using customer details from online applications.

Data Science Challenge from Coursera Project : Loan Default Prediction

A model for predicting loan default based on historical data.

Credit Risk Analysis - PD Modelling

Data science workflow development to solve credit load default problem, as part of the interview assignment

The project predicts the probability of loan default using various financial features of customer. I applied SMOTENN by combining SMOTE and Edited Nearest Neighbor (ENN) to handle class imbalance. Logistic Regression, Random Forest and CATBOOST models have been apllied and evaluated based on accuray, F1 score, ROC-AUC score.

A project to compare machine learning algorithms for a loan default dataset using MATLAB.

Goal is to determine whether client (Lending Club) should invest in P2P loans.

Predictive model for loan defaulters using LightGBM, HyperOpt and SHAP model interpretation.