In this project we try to predict home credit default risk for clients. We try to predict, if the client will have payment difficulties or not.

Example using Optuna to tune hyper parameters for LightGBM

Machine Learning Model for predicting the estimated amount for renting a bicycle as a function of various parameters like the day of the week, wind speed, temperature, etc.

Photometric light curves classification with machine learning

Accommodating supervised learning algorithms for the historical prices of the world's favorite cryptocurrency and boosting it through LightGBM.

[Information System] SMUTF: Schema Matching Using Generative Tags and Hybrid Features

Disease risk prediction autoML based on Lightgbm,Optuna ,Shap value and MLflow

ML classification project identifying term deposit customers for a bank.

A LightGBM-based bot classifier implementation for Twitter.

Predict students' dropout and academic success using LightGBM

We will be making use of Spotify API (Spotipy) accompanied by Python to get data from Spotify Web API. Based on the data extracted from each music we planned to analyse various audio features and patterns of the music.

Run histogram-based gradient boosted trees binary classifier on generated data and interpret results with standard metrics, SHAP, and supervised clustering

Contains the code file used for submission and feature engineering in the Home Credit Default Risk competition (rank 1029/7198; top 13%).

Rest API for predicting default scores

Developed an end-to-end ML pipeline for Santander Customer Transaction Prediction problem using LightGBM, with a fully functional Streamlit UI and a FastAPI backend for real-time predictions.