[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

tools for scalable and non-intrusive parameter estimation, uncertainty analysis and sensitivity analysis

AI-CryptoTrader is a state-of-the-art cryptocurrency trading bot that uses ensemble methods to make trading decisions based on multiple sophisticated algorithms. Built with the latest machine learning and data science techniques, AI-CryptoTrader provides a powerful toolset and advanced trading stratgies for maximizing your cryptocurrency profits.

Handwritten digit recognition with MNIST & Keras

Winning 2nd place🥈at NUS CS5228 in-class Kaggle competition 2018!

A unified framework for tabular, time-series, and multimodal machine learning

2nd place · Detect AI-generated text across 6 classes · ModernBERT + LDAM + per-class ensemble · Macro F1 0.95919 — MALTO Hackathon, Politecnico di Torino

f1 race winner predictor

AI Firewall and guardrails for LLM-based Elixir applications

This repository contains practical implementations of core machine learning algorithms and techniques, created for learning and practice purposes.

This project focuses on using the AWS open-source AutoML library, AutoGluon, to predict bike sharing demand using the Kaggle Bike Sharing demand dataset.

46 projects on a full spectrum of Advanced Data Science, AI, Machine Learning, Deep Learning skills, including EDA, Data Visualization, traditional ML Fundamentals (Regression, Classification, Clustering, Ensemble methods) using TensorFlow/Keras, PyTorch, Scikit-Learn, Pandas, NumPy, & more, implemented in Python scripts & Jupyter Notebooks.k

🛰️ Production-ready ML system for geomagnetic storm prediction | 98% AUC, 70% recall | Threshold-optimized ensemble with real-time inference | 29-year dataset (1996-2025) | NOAA SWPC operational standards | Complete MLOps pipeline

Time series forecasting with Fourier-adjusted time dummies

Project for Titanic survival prediction, achieving 83.28% accuracy through advanced feature engineering, hyperparameter optimization, and ensemble methods.

Mathematical theory, code examples, and production implementations of classification, regression, trees, SVMs, ensemble methods, and neural networks

Experimentation tool for exploring multi-model LLM deliberation + social choice voting

This project studies different possibilities to make good predictions based on machine learning algorithms, but without requiring great theoretical knowledge from the users. Moreover, a software package that implements the prediction process has been developed. The software is an ensemble method that first predicts a value taking into account different algorithms at the same time, and then it combines their results considering also the previous performance of each algorithm to obtaina final prediction of the value. Moreover, the solution proposed and implemented in this project can also predict according to a concrete objective (e.g., optimize theprediction, or do not exceed the real value) because not every prediction problem is subject to the same constraints. We have experimented and validated the implementation with three different cases. In all of them, a better performance has been obtained in comparison with each of the algorithms involved, reaching improvements of 45 to 95%.

Capstone project #2 for the Harvard University Professional Certificate in Data Science

A financial fraud detection & credit risk scoring system utilizing a variety of techniques

User documentation website for the Sulis tier 2 HPC service. Built using Jekyll.

Production-ready ML pipeline for telco customer churn prediction using advanced ensemble methods (XGBoost, CatBoost, Random Forest). Handles class imbalance, provides business insights, and includes modular MLOps architecture. Built with scikit-learn, featuring comprehensive EDA, feature engineering, and business impact analysis.

Ensemble Deep Random Vector Functional Link with Skip Connections (edRVFL-SC) No GPU required • 100× faster training

Comparison of ensemble learning methods on diabetes disease classification with various datasets

Official Implementation of Track2Vec: Fairness Music Recommendation with a GPU-Free Customizable-Driven Framework EvalRS-CIKM-2022

🎯 PSOD: Pseudo-Supervised Outlier Detection library for tabular data. Novel approach using ensemble regression prediction errors as outlier scores. Supports mixed data types, multiple transformations, and comprehensive visualization tools.

Predict sale prices via regression models, using PCA, k-means clustering, ensemble models, pipelines, etc.

Build a classification model to predict clients who are likely to default on their loans. Give recommendations to the bank on important features to consider while approving a loan. Concepts Used: Logistic Regression, Decision Trees, Random Forests, and Ensemble Methods

Fairness and bias detection library for Elixir AI/ML systems

Anomaly Detection Advanced - Professional Python project