ProphitBet is a Machine Learning Soccer Bet prediction application. It analyzes the form of teams, computes match statistics and predicts the outcomes of a match using Advanced Machine Learning (ML) methods. The supported algorithms in this application are Neural Networks, Random Forests & Ensembl Models.

[ICDE'20] ⚖️ A general, efficient ensemble framework for imbalanced classification. | 泛用，高效，鲁棒的类别不平衡学习框架

[NeurIPS’20] ⚖️ Build powerful ensemble class-imbalanced learning models via meta-knowledge-powered resampler. | 设计元知识驱动的采样器解决类别不平衡问题

Bank customers churn dashboard with predictions from several machine learning models.

Experimental implementations of several (over/under)-sampling techniques not yet available in the imbalanced-learn library.

This project builds a machine learning system to detect credit card fraud transactions using an imbalanced dataset, applying SMOTE for class balancing and comparing Logistic Regression and Random Forest models.

An Intrusion Detection System (IDS) using ensemble machine learning models and LIME for explainable AI, leveraging the CICIDS-2017 dataset for network intrusion detection with transparent predictions.

Fairness-aware ICU mortality prediction using MIMIC-III data and Group-Aware SMOTE

Testing different supervised machine learning algorithms to predict credit risk

Conception and deployment of a credit-scoring model, API and interactive dashboard

End-to-end ML pipeline for car evaluation & recommendation — clustering, feature selection, imbalance handling, and boosting ensembles with a Flask + HTML frontend.

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

Investigates age‑group differences in support for renewable energy transition and builds predictive models to identify key demographic and attitudinal predictors of support for stronger climate commitments for the UNDP Peoples’ Climate Vote 2024 dataset.

Loan Default Prediction: Predict loan default risk using classification models with feature engineering, model training, and evaluation metrics.

A machine learning web app that predicts whether a telecom customer will churn or not. It uses a Random Forest model trained on the IBM Telco dataset, handles class imbalance with SMOTE, and is deployed as an interactive Streamlit app where users input customer details and get a simple Yes / No prediction.

Identify credit card risk using Machine Learning algorithms

ML classification model served via FastAPI, containerized with Docker and deployed on Hugging Face Spaces — includes PostgreSQL tracing, CI/CD with GitHub Actions, and full pytest coverage

A full stack classification machine learning project.

Credit card fraud detection using SMOTE, Logistic Regression, Random Forest and XGBoost on 284k transactions