⚽ A machine learning project that predicts the 2026 FIFA World Cup using FIFA rankings, historical match results, Poisson regression, and Monte Carlo simulation.
An AI-driven healthcare tool that predicts early symptoms of diseases based on user input. Uses ML classification on patient data and symptom patterns for prediction and prevention suggestions.
ChurnSense-AI: End-to-end telecom churn prediction system with XGBoost, SHAP explainability, SQL analytics, Power BI dashboards, and customer risk intelligence.
End-to-End MLOps Pipeline: Train, track, containerize, and deploy ML models via FastAPI REST API with automated CI/CD on Render.
An end-to-end Machine Learning application that predicts the likelihood of heart disease based on patient medical attributes. The project demonstrates the complete ML workflow, including data preprocessing, exploratory data analysis, model training, evaluation, and deployment through a user-friendly Flask web application.
AI-powered IPL analytics platform with match prediction, team/player insights, and Explainable AI (XAI) — built with Flask, scikit-learn & Plotly.
End-to-end ML project that classifies emails as Spam or Not Spam using NLP, TF-IDF, Logistic Regression and Streamlit.
Simple IA de détection de spam
Network Intrusion Detection System (NIDS) is a machine-learning-based system for detecting malicious network traffic in real time. The system uses the CIC-IDS2017 dataset to train supervised learning models and combines packet capture, flow generation, feature extraction, ML-based classification, alerting, and automated IP blocking into a single pi
Customer Segmentation using K-Means Clustering with Python and Scikit-Learn
End-to-end NLP project for classifying consumer financial complaints using TF-IDF, Logistic Regression, and SBERT.
Cost-sensitive ML pipeline for diabetes risk classification — custom 5:1 false-negative penalty, threshold optimization, and SHAP interpretability on a 100K-patient dataset
End-to-end machine learning project for credit risk prediction using Logistic Regression, Random Forest, Gradient Boosting, SMOTE, and model interpretability.
Python-based sales analytics project that transforms raw sales data into actionable business insights through data cleaning, KPI analysis, and interactive visualizations.
Collection of machine learning tasks covering classification, regression, clustering, feature engineering, and model evaluation.
Implement Support Vector Machines using Scikit-Learn in Python to perform both binary (2-class) and multi-class (all 10 classes) image classification on CIFAR-10.
AI-powered Parkinson’s disease detection system using spiral drawing analysis with CNN, Random Forest, and Logistic Regression, featuring risk assessment, medical chatbot, doctor consultation, and automated reports.
Fine-tuned DistilBERT for political misinformation classification with cross-dataset evaluation across LIAR and Fakeddit benchmarks, compared against Logistic Regression, Naive Bayes, and SVM baselines.
Cost-sensitive credit-card fraud detection: tuned LightGBM + a dollar-cost-optimized decision threshold, with a live interactive dashboard.
A supervised machine learning pipeline for potential fraud-risk classification using SMOTE, Logistic Regression, and Random Forest.
To associate your repository with the skikit-learn topic, visit your repo's landing page and select "manage topics."