Credit risk analysis for credit card applicants

Application to finance

The aim is to understand which are the key factors for a certain level of credit risk to occur. In addition, some ML models capable to predict the credit risk level for a company in an year - given past years data - have been built and compared.

Predicting how much loan will be approved

Reverse engineering of the FICO algorithm

Predicting the ability of a borrower to pay back the loan through Traditional Machine Learning Models and comparing to Ensembling Methods

The project involved developing a credit risk default model on Indian companies using the performance data of several companies to predict whether a company is going to default on upcoming loan payments.

In 2019, more than 19 million Americans had at least one unsecured personal loan. Personal lending is growing at an extremely fast rate, and FinTech firms need to go through an organize large amounts of data in order to optimize lending. Python will be used to evaluate several machine learning models to predict credit risk. Algorithms such as Ra…

Credit risk poses a classification problem that’s inherently imbalanced. Using a dataset of historical lending activity from a peer-to-peer lending services company, build a model that can identify the creditworthiness of borrowers.

Credit Risk Analysis - PD Modelling

A data analysis project to classify whether an applicant is capable of paying a home loan by using 4 machine learning models (Logistic Regression, SVM, Random Forest and LGBM) and 1 deep learning model (DeepFM). We also drew some insights from the best model that can be useful for analysts in bank.

This project focuses on credit risk analysis using SQL, Python, and Power BI. We built an end-to-end pipeline that starts with raw loan applicant data and ends with an interactive dashboard for stakeholders to monitor loan defaults.

This project predicts credit risk based on user inputs and categorize loan applications into Poor, Average, Good, and Excellent categories. The project mirrors the CIBIL scoring system.

Credit risk analysis using scikit-learn and imbalanced-learn.

Credit risk analysis determines a borrower's ability to meet debt obligations and the lender's aim when advancing credit. The goal is to identify patterns that indicate if a person is unlikely to repay the loan or labeled as a bad risk through automated machine learning algorithms.

Machine Learning pipelines are deployed to accomplish the objective of credit risk analysis.

Our group chose this question to bring attention to the little knowledge that young loan applicants have. Based on our findings in our models we explore: Which age group is the least likely to apply for loans? Which group is most likely to default on loans?

ML course project

This repository contains projects related to data mining. Data mining finds valuable information hidden in large volumes of data and it is the analysis of data and the use of software techniques for finding patterns and regularities in sets of data.