Pfeed: Generating near real-time personalized feeds using precomputed embedding similarities
This work addresses real-time personalization for e-commerce platforms, offering an incremental improvement to existing embedding-based methods.
The paper tackled the challenges of limited diversity and high infrastructure costs in personalized recommender systems by proposing a method that dynamically updates customer profiles and composes feeds every two minutes using precomputed embeddings, resulting in a 4.9% uplift in conversions when deployed on an e-commerce platform.
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.