👕 Open-source course on architecting, building and deploying a real-time personalized recommender for H&M fashion articles.

Correcting the LogQ Correction: Revisiting Sampled Softmax for Large-Scale Retrieval (RecSys'25)

A Movie Recommender System using YouTube's Two-Tower Architecture built with TFRS+TFR and served with FastAPI

Policy recommendation using Two Tower Neural Network and Configurable business heuristics for SBI Hackathon (Rank 3).

Policy recommendation system inspired by YouTube's algorithm, using Two-Tower Neural Networks and heuristics, developed for the SBI Life Hackathon'25

Repository for Computer Science Master Thesis

Movie recommendation app that utilizes machine-learning to recommend new movies.

Two-Tower RecSys + FAISS retrieval + cold-start demo (Amazon Video Games 2023)

Sistema experimental para recolectar datos públicos de Sputnik y generar recomendaciones de discos // Experimental system for collecting public data from Sputnik and generating release recommendations

A content recommendation engine using two-tower neural networks, reactive Java, and event-driven architecture.

Two-Tower ESMM DNN Implementation for Ranking in Hotels Search

A two tower model and datasets generator for scholarship.id recommendation system

Tower-two and NeuralUCB hybrid to generate repository recomendations

Document search and retrieval with deep learning (part of ML institute programme)

A decoupled Two-Tower and SASRec architecture that isolates user data from item embeddings to enable "Right to be Forgotten" compliance via exact retraining.