# Metadata Embeddings for User and Item Cold-start Recommendations

arXiv: https://arxiv.org/abs/1507.08439 · HTML: https://mlsanity.com/paper/1507.08439/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2015.

## Built on by (most cited first, 29 of 29)

- [GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation](https://mlsanity.com/paper/2304.03879/) (2023)
- [AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding](https://mlsanity.com/paper/2106.02318/) (2021)
- [A Systematic Review and Replicability Study of BERT4Rec for Sequential Recommendation](https://mlsanity.com/paper/2207.07483/) (2022)
- [A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps](https://mlsanity.com/paper/2106.03819/) (2021)
- [Effective and Efficient Training for Sequential Recommendation using Recency Sampling](https://mlsanity.com/paper/2207.02643/) (2022)
- [From Variability to Stability: Advancing RecSys Benchmarking Practices](https://mlsanity.com/paper/2402.09766/) (2024)
- [Blockchain-based Recommender Systems: Applications, Challenges and Future Opportunities](https://mlsanity.com/paper/2111.11509/) (2021)
- [Dynamic Slate Recommendation with Gated Recurrent Units and Thompson Sampling](https://mlsanity.com/paper/2104.15046/) (2021)
- [Online POI Recommendation: Learning Dynamic Geo-Human Interactions in Streams](https://mlsanity.com/paper/2201.10983/) (2022)
- [Multimodal Data Fusion in High-Dimensional Heterogeneous Datasets via Generative Models](https://mlsanity.com/paper/2108.12445/) (2021)
- [Private Matrix Factorization with Public Item Features](https://mlsanity.com/paper/2309.11516/) (2023)
- [RePlay: a Recommendation Framework for Experimentation and Production Use](https://mlsanity.com/paper/2409.07272/) (2024)
- [A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges](https://mlsanity.com/paper/2507.21117/) (2025)
- [AgentSelect: Benchmark for Narrative Query-to-Agent Recommendation](https://mlsanity.com/paper/2603.03761/) (2026)
- [Extreme Multilabel Classification for Specialist Doctor Recommendation with Implicit Feedback and Limited Patient Metadata](https://mlsanity.com/paper/2308.11022/) (2023)
- [Towards Inductive Robustness: Distilling and Fostering Wave-induced Resonance in Transductive GCNs Against Graph Adversarial Attacks](https://mlsanity.com/paper/2312.08651/) (2023)
- [Generalized User Representations for Transfer Learning](https://mlsanity.com/paper/2403.00584/) (2024)
- [Exploring Customer Price Preference and Product Profit Role in Recommender Systems](https://mlsanity.com/paper/2203.06641/) (2022)
- [Dynamic collaborative filtering Thompson Sampling for cross-domain advertisements recommendation](https://mlsanity.com/paper/2208.11926/) (2022)
- [Tag-Aware Document Representation for Research Paper Recommendation](https://mlsanity.com/paper/2209.03660/) (2022)
- [M-LLM3REC: A Motivation-Aware User-Item Interaction Framework for Enhancing Recommendation Accuracy with LLMs](https://mlsanity.com/paper/2508.15262/) (2025)
- [Gender In Gender Out: A Closer Look at User Attributes in Context-Aware Recommendation](https://mlsanity.com/paper/2207.14218/) (2022)
- [Beer2Vec : Extracting Flavors from Reviews for Thirst-Quenching Recommandations](https://mlsanity.com/paper/2208.04223/) (2022)
- [Lib-SibGMU -- A University Library Circulation Dataset for Recommender Systems Developmen](https://mlsanity.com/paper/2208.12356/) (2022)
- [Job recommendations: benchmarking of collaborative filtering methods for classifieds](https://mlsanity.com/paper/2301.07946/) (2023)
- [Predicting IPv4 Services Across All Ports](https://mlsanity.com/paper/2303.00895/) (2023)
- [MFAI: A Scalable Bayesian Matrix Factorization Approach to Leveraging Auxiliary Information](https://mlsanity.com/paper/2303.02566/) (2023)
- [On the Reliability of Sampling Strategies in Offline Recommender Evaluation](https://mlsanity.com/paper/2508.05398/) (2025)
- [Do Recommendation Algorithms Work When Users Are LLM Agents? A Case Study on Moltbook](https://mlsanity.com/paper/2606.29762/) (2026)

## Abstract (arXiv)

I present a hybrid matrix factorisation model representing users and items as linear combinations of their content features' latent factors. The model outperforms both collaborative and content-based models in cold-start or sparse interaction data scenarios (using both user and item metadata), and performs at least as well as a pure collaborative matrix factorisation model where interaction data is abundant. Additionally, feature embeddings produced by the model encode semantic information in a way reminiscent of word embedding approaches, making them useful for a range of related tasks such as tag recommendations.