This repository contains the core model we called "Collaborative filtering enhanced Content-based Filtering" published in our UMUAI article "Movie Genome: Alleviating New Item Cold Start in Movie Recommendation"

Accompanying code for reproducing experiments from the HybridSVD paper. Preprint is available at https://arxiv.org/abs/1802.06398.

Hybrid recommendation engine using deep learning that incorporates user and item features, including images and text.

Recommendation System using ML and DL

This repository contains all the code used in the Recommender System challenge of the Recommender System exam at PoliMi.

A modular, explainable recommendation pipeline leveraging multiple strategies—collaborative filtering, embeddings, and fallback logic—for robust, personalized product recommendations in real-world scenarios.

MelodyMind offers personalized music recommendations, from a real-time Last.fm API-powered app to an advanced hybrid system combining content-based and collaborative filtering with LightFM.

"A hybrid recommendation system enhancing personalized music suggestions using collaborative and content-based filtering."

Movie recommendation system with Python. Implements content-based filtering (TF-IDF + cosine similarity), collaborative filtering with matrix factorization (TruncatedSVD), and a hybrid approach. Evaluates with Precision@K, Recall@K, and NDCG. Includes rating distribution plots, top movies, and sample recommendations.

🎵 A hybrid recommendation system for Amazon Digital Music (2023) combining TF-IDF, collaborative filtering, and popularity models into an interactive Streamlit app.

A full-stack hybrid book recommender system combining collaborative filtering (ALS), content-based similarity (SBERT), and machine learning ranking (CatBoost). Backend: FastAPI • Frontend: Streamlit • Vector DB: Qdrant • Model serving • Cold-start fallback • Book metadata display.

Hybrid book recommendation system using NLP (TF-IDF, cosine similarity) and collaborative filtering (SVD) to generate personalized book suggestions with high accuracy. Includes full EDA, model evaluation.

🍽️ ML-powered restaurant recommendation system that reduces decision fatigue by 40%. Hybrid approach combining collaborative filtering, content-based filtering, and contextual signals. Complete PM portfolio project with PRD, evaluation, and Streamlit demo.

Hybrid Movie Recommender est une application full-stack qui génère des recommandations personnalisées de films en fusionnant des signaux content-based et collaborative filtering. Le projet comprend une API (Python), une interface web (TypeScript) et des scripts de préparation/gestion des données.

MOVIE-PULSE-HYBRID-INTELLIGENCE-MATRIX: movie recommendation engine blending NLP-driven Content Filtering and SVD Matrix Factorization. Features Streamlit Enterprise UI, dual-strategy processing, real-time logic analytics

A Hybrid Anime Recommender System using content-based and collaborative filtering, built with end-to-end MLOps practices. Integrates Comet-ML for experiment tracking, DVC for data/model versioning, Jenkins for CI/CD, and Kubernetes for scalable deployment.

A lightweight recommender that helps you discover your next learning resource. It blends patterns from similar users with content keywords, and explains each suggestion in the UI.

Multi-algorithm recommendation system: collaborative filtering (ALS, SVD), content-based, hybrid with cold-start handling, A/B evaluation framework