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

• URL: http://arxiv.org/abs/2508.03702v1
• Date: Sat, 19 Jul 2025 19:03:38 GMT
• Title: Suggest, Complement, Inspire: Story of Two Tower Recommendations at Allegro.com
• Authors: Aleksandra Osowska-Kurczab, Klaudia Nazarko, Mateusz Marzec, Lidia Wojciechowska, Eliška Kremeňová,
• Abstract summary: This paper presents a unified content-based recommendation system deployed at Allegro.com, the largest e-commerce platform of European origin.<n>We show how the same model architecture can be adapted to serve three distinct recommendation tasks.<n>Our results show that a flexible, scalable architecture can serve diverse user intents with minimal maintenance overhead.
• Score: 39.58317527488534
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• OneSearch: A Preliminary Exploration of the Unified End-to-End Generative Framework for E-commerce Search [43.94443394870866]
  OneSearch is the first industrial-deployed end-to-end generative framework for e-commerce search.<n>OneSearch reduces operational expenditure by 75.40% and improves Model FLOPs Utilization from 3.26% to 27.32%.<n>The system has been successfully deployed across multiple search scenarios in Kuaishou, serving millions of users.
  arXiv  Detail & Related papers  (2025-09-03T11:50:04Z)
• OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion [22.63172274938755]
  OneSug is an end-to-end generative framework for e-commerce query suggestion.<n>OneSug has been successfully deployed for the entire traffic on the e-commerce search engine in Kuaishou platform for over 1 month.
  arXiv  Detail & Related papers  (2025-06-07T20:24:05Z)
• AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Search [58.98450205734779]
  Large language model (LLM) agents have demonstrated strong capabilities across diverse domains.<n>Existing agent search methods suffer from three major limitations.<n>We introduce a comprehensive framework to address these challenges.
  arXiv  Detail & Related papers  (2025-06-06T12:07:23Z)
• Trinity-RFT: A General-Purpose and Unified Framework for Reinforcement Fine-Tuning of Large Language Models [65.90917869715258]
  Trinity-RFT is a general-purpose, unified and easy-to-use framework designed for reinforcement fine-tuning (RFT) of large language models.<n>It is built with a modular and decoupled design, consisting of an RFT-core that unifies and generalizes synchronous/asynchronous, on-policy/off-policy, and online/offline modes of RFT.
  arXiv  Detail & Related papers  (2025-05-23T12:41:09Z)
• Breaking Information Cocoons: A Hyperbolic Graph-LLM Framework for Exploration and Exploitation in Recommender Systems [41.43693025937088]
  HERec is a hyperbolic graph-LLM framework that effectively balances exploration and exploitation in recommender systems.<n>Our framework introduces two key innovations: (1) a semantic-enhanced hierarchical mechanism that aligns rich textual descriptions with collaborative information directly in hyperbolic space.<n>Experiments demonstrate that HERec consistently outperforms both Euclidean and hyperbolic baselines.
  arXiv  Detail & Related papers  (2024-11-21T06:01:47Z)
• Multi-criteria recommendation systems to foster online grocery [0.0]
  The purpose of recommending a product is to designate the most appropriate designation for a specific product. In this paper, we transform the product data using two methods of document representation: bag-of-words (BOW) and the neural network-based document combination known as vector-based (Doc2Vec) For our evaluation, we have compared the performance of these three criteria for each document representation method, discovering that the neural network-based (Doc2Vec) performs better and completely alters the results.
  arXiv  Detail & Related papers  (2023-12-12T17:40:16Z)
• ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest [60.841761065439414]
  At Pinterest, we build a single set of product embeddings called ItemSage to provide relevant recommendations in all shopping use cases. This approach has led to significant improvements in engagement and conversion metrics, while reducing both infrastructure and maintenance cost.
  arXiv  Detail & Related papers  (2022-05-24T02:28:58Z)
• One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking [97.60915598958968]
  We propose a one-shot neural ensemble architecture search (NEAS) solution that addresses the two challenges. For the first challenge, we introduce a novel diversity-based metric to guide search space shrinking. For the second challenge, we enable a new search dimension to learn layer sharing among different models for efficiency purposes.
  arXiv  Detail & Related papers  (2021-04-01T16:29:49Z)
• AutoRC: Improving BERT Based Relation Classification Models via Architecture Search [50.349407334562045]
  BERT based relation classification (RC) models have achieved significant improvements over the traditional deep learning models. No consensus can be reached on what is the optimal architecture. We design a comprehensive search space for BERT based RC models and employ neural architecture search (NAS) method to automatically discover the design choices.
  arXiv  Detail & Related papers  (2020-09-22T16:55:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.