Suggest, Complement, Inspire: Story of Two Tower Recommendations at Allegro.com

Abstract

Building large-scale e-commerce recommendation systems requires addressing three key technical challenges: (1) designing a universal recommendation architecture across dozens of placements, (2) decreasing excessive maintenance costs, and (3) managing a highly dynamic product catalogue. This paper presents a unified content-based recommendation system deployed at Allegro.com, the largest e-commerce platform of European origin. The system is built on a prevalent Two Tower retrieval framework, representing products using textual and structured attributes, which enables efficient retrieval via Approximate Nearest Neighbour search. We demonstrate how the same model architecture can be adapted to serve three distinct recommendation tasks: similarity search, complementary product suggestions, and inspirational content discovery, by modifying only a handful of components in either the model or the serving logic. Extensive A/B testing over two years confirms significant gains in engagement and profit-based metrics across desktop and mobile app channels. Our results show that a flexible, scalable architecture can serve diverse user intents with minimal maintenance overhead.

Recsys 2025 Industrial Track

References in corpus (8)

• Deep Learning Recommendation Model for Personalization and Recommendation Systems
• PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest
• The Faiss library
• Personalized Embedding-based e-Commerce Recommendations at eBay
• Semi-supervised Adversarial Learning for Complementary Item Recommendation
• Deep Item-based Collaborative Filtering for Sparse Implicit Feedback
• Taming the One-Epoch Phenomenon in Online Recommendation System by Two-stage Contrastive ID Pre-training
• 360Brew: A Decoder-only Foundation Model for Personalized Ranking and Recommendation