Project for real-time anomaly detection using Kafka and python
This is End to end project for potato disease detection using deep learning. I build cnn model to predict potato 3 classes early-blight, late-blight and healthy.
Machine Learning-powered car price prediction web app built with Flask, Scikit-learn, and feature engineering for real-time resale price estimation.
Features injected recurrent neural networks for short-term traffic speed prediction
AI-powered phishing URL detection system using Machine Learning and Streamlit that analyzes website URLs and predicts whether they are safe or phishing.
π€ AI-powered smart lighting system with 85-96% occupancy prediction, 30-50% energy savings, weather integration, and real-time optimization. Built with React, Flask, and Machine Learning.
Churn prediction pipeline with Python and scikit-learn. Focus on data processing, modeling and analysis.
βAn independent predictive sports analytics model designed to classify table tennis match dynamics and evaluate player tactical features"
Machine learning project. Learn to deploy and serve a trained model, save and load model artifacts, wrap a model in a FastAPI service, and handle inputs, validation, and prediction requests.
AI-Powered Audio Deepfake Detection System built with Python, Flask, librosa, scikit-learn and SQLite
IBM stock price forecasting using Random Forest, LSTM (4-layer), and ARIMA models with Python
This project builds multiple ML classification models to predict visa approval outcomes using the EasyVisa dataset. The repository includes the full notebook, documentation, and results.
SwiftLearning is iOS side of scikit-learning
End-to-end speech emotion recognition pipeline using Librosa & Scikit-Learn with 180-D acoustic feature extraction, split-window analysis, and an active learning retraining loop.
AnΓ‘lise exploratΓ³ria (em inglΓͺs) do dataset Heart Disease UCI. Foram analisados fatores que podem estar associados a doenΓ§as cardΓacas e foi criado um modelo para classificar a presenΓ§a de doenΓ§as cardΓacas em novos pacientes.
ππ’π―ππ« ππ’π«π«π‘π¨π¬π’π¬ ππ«πππ’πππ’π¨π§
A machine learning project that predicts wine quality (good vs bad) using physicochemical properties. Built using Python, Pandas, Scikit-learn, with models like Random Forest and SVM, including data preprocessing, feature engineering, scaling, and hyperparameter tuning. machine-learning classification python scikit-learn data-science ml-project
Industrial Distribution & Operations Intelligence Platform
To associate your repository with the scikit-learning topic, visit your repo's landing page and select "manage topics."