TFM Comparativa de modelos de Machine Learning interpretables en riesgo crediticio

An analysis and prediction model for the Statlog (German Credit Data) dataset problem

Home Credit Default Risk project is to correctly offer loans to individuals who can pay back and turn away those who cannot

Credit risk analysis with R

The objective project is to decrease the company's losses by up to 30% through bad loans by creating a machine learning system to assist in automating loan assessments

Credit Risk Analysis using Python

As an intern Data Scientist at ID/X Partners, I'm involved involved in a project from a lending company to build a model that can predict credit risk using a dataset provided by the company which consists of data on loans accepted and rejected.

Data Analytics For Finance

This repository contains the Python scripts that I have written and run to execute a series of analytic model developments using datasets taken from the book "The Elements of Statistical Elements" by Hastie, Tibshirani, Friedman

Sample of Credit Risk model created with Scikit Learn allowing inference API with Flask.

We analyse unsecured peer to peer lending data with credit history, financial, historical and loan request application information at Lending Club, to study patterns characterizing borrower behaviour on the platform following the data science process. We specifically focus our attention on credit risk and identifying the key drivers behind the d…

This repo is about deploying web app written by Flask on Heruko cloud platform.

Portfolio project: Machine learning automation project for a lending company. Automated the calculation of fees that make each new transaction/customer profitable by predicting the expected financial loss based on probability of default, loss given default, and exposure at default risk models.

Project-Based Intern from Home Credit Indonesia, Credit Risk Classification based on bad/good credit

Heavily imbalanced credit dataset was resampled, six machine learning models were fit to training data to predict credit risk. A suggestion was made based on the accuracy of predictions from each model.

Build a machine learning model that can automatically assess loans with goal to predict client’s repayment abilities and speed up inspection filing without spending more money.

Credit Default Approximation for Unsecured Lending Built Machine Learning Classification models (Random Forest, LGBM, XGBoost) in Python to assess the probability of credit defaults.

A model for predicting loan default based on historical data.

Data Analysis project analyzing the characteristics of credit card borrowers. After the analysis, a classification model is built.