Recommendation System using ML and DL

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.

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.

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.

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"

Movie recommendation engine featuring a 6-model hybrid ensemble (SBERT semantic, turbovec vector search, Collaborative Filtering, PageRank, Content, Knowledge Graph) with FastAPI & React Vite. Powered by PySpark MLOps.

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.

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.

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

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.

Production-style movie recommendation engine built with Hybrid Recommenders, FastAPI, Streamlit, and MovieLens. Features collaborative filtering, content-based recommendations, model evaluation, and interactive recommendations.

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

A multimodal hybrid movie recommendation engine that combines Collaborative Filtering, Content-Based Filtering, and a Hybrid Fusion layer, with genuine multimodal features via OpenAI CLIP (poster images + text metadata).

Hybrid product recommender system combining SVD-based collaborative filtering, TF-IDF content-based filtering, candidate generation, offline evaluation, and an interactive Streamlit interface.

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

Hybrid recommendation system built with PyTorch, FastAPI, and PostgreSQL using Neural Matrix Factorization with collaborative and content-based filtering.

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

A production-grade hybrid recommendation engine combining Item-Item Collaborative Filtering with semantic content relevance, stabilized by an ML-based veto ranker to filter out noisy interaction data