Pfeed: Generating Near Real-time Personalized Feeds Using Precomputed Embedding Similarities

Abstract

In personalized recommender systems, embeddings are often used to encode customer actions and items, and retrieval is then performed in the embedding space using approximate nearest neighbor search. However, this approach can lead to two challenges: 1) user embeddings can restrict the diversity of interests captured and 2) the need to keep them up-to-date requires an expensive, real-time infrastructure. In this paper, we propose a method that overcomes these challenges in a practical, industrial setting. The method dynamically updates customer profiles and composes a feed every two minutes, employing precomputed embeddings and their respective similarities. We tested and deployed this method to personalise promotional items at Bol, one of the largest e-commerce platforms of the Netherlands and Belgium. The method enhanced customer engagement and experience, leading to a significant 4.9% uplift in conversions.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygebre2024pfeed

Related papers

• Embedding In Recommender Systems: A Survey (2023)0.00
• Large-scale Real-time Personalized Similar Product Recommendations (2020)0.00
• Unified Embedding Based Personalized Retrieval In Etsy Search (2023)2.26
• Mixed-precision Embeddings For Large-scale Recommendation Models (2024)0.00
• Two Is Better Than One: Dual Embeddings For Complementary Product Recommendations (2022)6.34
• Async Learned User Embeddings For Ads Delivery Optimization (2024)0.00
• Plug-and-play Parameter-efficient Tuning Of Embeddings For Federated Recommendation (2025)0.95
• Pebr: A Probabilistic Approach To Embedding Based Retrieval (2024)0.00