[Up-to-date] A curated list of resources on cold-start recommendations.

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.

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.

[TKDE 2018] Code for "MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation"

Exploring market maker models for e-commerce dynamic pricing

[TMLR 2025] Node Duplication Improves Cold-start Link Prediction

Cold-start como tarefa de completude em grafos de conhecimento: uma abordagem via encoders rasos de propagação. Dissertação apresentada para conclusão do mestrado em ciência da computação no PPGCC da UFMG.

Like the idea?

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

Existing cross-domain recommendation methods rely on overlapping users and source interaction sequences to learn preference transfer function, leaving the rich structural information in pre-trained target-domain embeddings unexploited. In this paper, we propose COTA (Cluster Optimal Transport Alignment), a framework for cold-start CDR.

Implemented rank-based recommendation system and various collaborative filtering models using Python (NumPy, Pandas, Scikit-learn). Addressed sparsity and cold start problems. Evaluated models using MAE, RMSE, and precision metrics.

Matrix Factorization–based recommender system built from scratch and with cmfrec, evaluated using RMSE, Precision@K, and Recall@K on the Yelp dataset.

An intelligent recommender system based on deep denoising graph convolutional autoencoder and learning automata

A collaborative-filter-based music recommender machine

making of a recommendations retriever using embedding models and approx nearest neighbor library