Credit Risk Analysis with Machine Learning
-
Updated
May 2, 2023 - Jupyter Notebook
Credit Risk Analysis with Machine Learning
A full ML pipeline for customer churn prediction in telecom, banking, or SaaS. Includes robust data cleaning, automatic feature engineering, model training/tuning (Logistic Regression, RF, XGBoost), interpretability, and interactive dashboards for actionable business retention insights.
4 Boosting Algorithms You Should Know – GBM, XGBoost, LightGBM & CatBoost
SaleFore AI: Ultra-accurate sales forecasting using ensemble ML (XGBoost, LightGBM, CatBoost) with RTX 4060 GPU optimization. Achieves 88-95% accuracy with advanced hyperparameter tuning.
This project detects AI-generated text using an ensemble of classifiers: Multinomial Naive Bayes, Logistic Regression, LightGBM, and CatBoost. It includes robust data preprocessing, model development, and evaluation, ensuring accurate identification of AI-generated content from a diverse text dataset.
Flask API for real-time intrusion detection using a threshold-optimized LightGBM model.
Machine learning project for KTM Komuter hourly ridership prediction using regression models.
Goal Using the data collected from existing customers, build a model that will help the marketing team identify potential customers who are relatively more likely to subscribe term deposit and thus increase their hit ratio
predicting a continuous target (regression) based on number of anonymous features columns given in the data.
All Possible Machine Learning algorithms implementation in jupyter notebook with csv file.
End-to-end retail demand forecasting system — built so the accuracy number is trustworthy: leakage-safe features, rolling-origin walk-forward validation, an automated leakage audit that gates CI, drift monitoring, a latency-benchmarked FastAPI service, and a C++ vector-index cold-start engine for forecasting brand-new products — plus DSA-optimized
Reproducible machine learning pipeline for IoT/Windows dataset classification with leakage-aware evaluation.
🔍 Predict customer churn with a machine learning system that identifies at-risk clients and recommends tailored retention strategies for better ROI.
Analytics Vidhya AmExpert ML Competition
Machine Learning pipeline for financial transaction fraud detection. Incorporates SMOTE, ensemble models, neural networks.
End-to-end MLOps pipeline: LightGBM model served via FastAPI, containerised with Docker, deployed to Hetzner via GitHub Actions CI/CD
Stellar objects classification from sensor data taken by the SDSS (Sloan Digital Sky Survey) using some basic machine learning models.
Add a description, image, and links to the lightbgm topic page so that developers can more easily learn about it.
To associate your repository with the lightbgm topic, visit your repo's landing page and select "manage topics."