Suggest, Complement, Inspire: Story of Two Tower Recommendations at Allegro.com
This addresses the problem of reducing maintenance costs and managing dynamic product catalogues for large-scale e-commerce platforms like Allegro.com, though it is incremental as it builds on existing Two Tower methods.
The paper tackled the challenge of building a unified recommendation system for a large e-commerce platform by adapting a Two Tower retrieval framework to handle similarity search, complementary suggestions, and inspirational content, resulting in significant gains in engagement and profit metrics over two years of A/B testing.
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.