This is the repository of our article published in RecSys 2019 "Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches" and of several follow-up studies.

A recommender system built for book lovers.

This repository contains the code for building movie recommendation engine.

A repository for a machine learning project about developing a hybrid movie recommender system.

Designed a movie recommendation system using content-based, collaborative filtering based, SVD and popularity based approach.

A Hybrid recommendation engine built on deep learning architecture, which has the potential to combine content-based and collaborative filtering recommendation mechanisms using a deep learning supervisor

This is a book recommendation engine built using a hybrid model of Collaborative filtering, Content Based Filtering and Popularity Matrix.

Hybrid recommedation for talents

A Content Based And A Hybrid Recommender System using content based filtering and Collaborative filtering

A Hybrid Recommendation system which uses Content embeddings and augments them with collaborative features. Weighted Combination of embeddings enables solving cold start with fast training and serving

Repository for the Recommender Systems Challenge 2020/2021 @ PoliMi

Full-stack hybrid book recommendation system combining Collaborative Filtering and Content-Based Filtering with weighted hybrid scoring, modular data pipelines, and model persistence. Deployed via Flask with responsive HTML/CSS UI and integrated CI/CD for production-ready, scalable, and interactive recommendations.

Combines user-based and item-based recommendation systems to deliver personalized movie suggestions, utilizing user preferences and film characteristics.

Movie recommendation system based on hybrid recommender and clustering

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"

Architected a polyglot e-commerce platform integrating a React/RTK frontend, a Node.js backend, and a Python ML microservice. The platform's core is a hybrid, real-time recommendation system using Redis and pre-computed models to provide instant, personalized suggestions. The system is built for production with Stripe, AWS S3 & robust security

This repo contains my practice and template code for all kinds of recommender systems using SupriseLib. More complex and hybrid Recommender Systems can build on top of these template codes.

Recommendation System Algorithm

Built a hybrid recommendation system with LightFM library and customised loss functions to optimize performance on retail data."

Auto encoders based recommendation system

A hybrid recommender system for suggesting CDN (content delivery network) providers to various websites

Set of recommender systems

Comparison of performance evaluation of the baseline and hybrid recommendation systems using various metrics, to prove that hybrid systems perform better

This study aims to investigate the effectiveness of three Transformers (BERT, RoBERTa, XLNet) in handling data sparsity and cold start problems in the recommender system. We present a Transformer-based hybrid recommender system that predicts missing ratings and ex- tracts semantic embeddings from user reviews to mitigate the issues.

🚀 Production-ready hybrid recommender system for e-commerce. Combines collaborative filtering & content-based ML with FastAPI backend, React

Hybrid Recommendation System for IMDB data set In Python from Scratch (can be scaled to any applications)

Recommends movies using Collaborative and Content based filtering techniques

The objective of the competition was to create the best recommender system for a book recommendation service by providing 10 recommended books to each user. The evaluation metric was MAP@10.

This repository contains the code for a book recommendation system that uses natural language processing techniques to recommend books to users based on their preferences.

Amar deep architectures for hybrid recommenders with GNNs