The Evolution of Search Engines in E-Commerce: From Static Catalogs to Hybrid and Vector Architectures

Pavel Astakhov, Aleksejj Belokrylov, Fedor Krasnov

Abstract


This article is devoted to the evolution of search systems in e-commerce with a particular focus on the DIY (Do-It-Yourself) segment. It examines the transition from static catalogs and SEO-based approaches to modern hybrid architectures that integrate Learning-to-Rank methods, vector search, and multimodal models. Special attention is given to engineering challenges related to scalability, data freshness, and the integration of machine learning into industrial solutions. The novelty of the research lies in the formulation of a step-by-step transformation strategy for search systems, specifically adapted to the requirements of the DIY segment and grounded in the analysis of practices adopted by leading retailers (Amazon, Walmart, Wayfair, Home Depot, Alibaba, Ozon, Wildberries). In addition, the study advances research hypotheses and proposes an experimental protocol that bridges theoretical modeling with empirical validation and objective evaluation of search quality. Thus, the article combines historical and applied analysis, offers a comprehensive perspective on the development of search technologies, and identifies promising directions for their application in the context of increasingly complex user queries and dynamic

Full Text:

PDF (Russian)

References


Liu T.-Y. Learning to Rank for Information Retrieval. Foundations and Trends in Information Retrieval, Vol. 3, No. 3, 2009, pp. 225–331. DOI: 10.1561/1500000016 .

Qin T., Liu T.-Y., Xu J., Li H. LETOR: A Benchmark Collection for Research on Learning to Rank for Information Retrieval. Information Retrieval Journal, 2010.

Wu L., Hu X., Shen D. Turning Clicks into Purchases: Revenue Optimization for Product Search in E-Commerce. Proceedings of ACM SIGIR, 2018. DOI: 10.1145/3209978.3209993 .

Johnson J., Douze M., Jégou H. Billion-scale similarity search with GPUs //IEEE Transactions on Big Data. – 2019. – Т. 7. – №. 3. – С. 535-547.

Linden G., Smith B., York J. Amazon.com recommendations: item-to-item collaborative filtering. IEEE Internet Computing, 2003.

Smith B., Linden G. Two decades of recommender systems at Amazon. com //Ieee internet computing. – 2017. – Т. 21. – №. 3. – С. 12-18.

Douze M. et al. The faiss library //arXiv preprint arXiv:2401.08281. – 2024.

The Home Depot. Home Depot introduces improved search for all. Corporate News, 2022. https://corporate.homedepot.com/news/products/home-depot-introduces-improved-search-all (date of access: 01.10.2025).

Wayfair Tech. Search & Recommender Systems. Wayfair Tech Blog, 2018–2022. https://www.aboutwayfair.com/careers/tech-blog/wayfair-paper-accepted-at-recsys-2022-applies-state-of-the-art-method-to-generate-product-recommendations (date of access: 01.10.2025).

Mozolevskyi D., AlShikh W. Comparative analysis of retrieval systems in the real world //arXiv preprint arXiv:2405.02048. – 2024.

Xu E. et al. Optimizing E-commerce Search: Toward a Generalizable and Rank-Consistent Pre-Ranking Model //Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. – 2024. – С. 2875-2879.

Zhang X. et al. A Survey on Side Information-driven Session-based Recommendation: From a Data-centric Perspective //IEEE Transactions on Knowledge and Data Engineering. – 2025.

Hybrid Search for an E-Commerce Product Catalogue. Elastic Search Labs, 2024. https://www.elastic.co/search-labs/blog/hybrid-search-ecommerce (date of access: 01.10.2025).

Recipes to vectors: Building a hybrid search app with OpenSearch. OpenSearch Blog, 2025. https://opensearch.org/blog/recipes-to-vectors-building-a-hybrid-search-app-with-opensearch/ (date of access: 01.10.2025).

What is vector search? Complete guide [2025]. Meilisearch Blog, 2025. https://www.meilisearch.com/blog/what-is-vector-search (date of access: 01.10.2025).

Ozon Tech Intro Meetup: How Search, Recommendations, and Advertising Work Ozon Tech Blog, 2023. https://habr.com/ru/companies/ozontech/articles/750196/ (date of access: 01.10.2025).

Krasnov F. V. H1: hybrid retrieval system for product search in e-commerce //Proceedings of the Institute for System Programming of the RAS. – 2024. – Т. 36. – №. 5. – С. 227-240.

Cheng Y., et al. An End-to-End Solution for Named Entity Recognition in eCommerce Search. Proceedings of the AAAI Conference on Artificial Intelligence, 2021.

Lin Z., et al. Research on the Evolution Path of Business Ecosystem of Platform Enterprises: A Case Study of Alibaba. Advances in Social Science, Education and Humanities Research, 2021.

Kwong R., Lee E. W. J. Legitimacy building and e-commerce platform development in China: The experience of Alibaba. Technological Forecasting and Social Change, 2020.

Yang L., et al. Personalized Embedding-based e-Commerce Recommendations at eBay. arXiv preprint, 2021.

Ding, S., Attenberg, J., & Baeza-Yates, R. WANDS: Dataset for Product Search Relevance Assessment. Advances in Information Retrieval, Vol. 13185, 2022, pp. 128-141.

Wang Z. et al. Semantic Ads Retrieval at Walmart eCommerce with Language Models Progressively Trained on Multiple Knowledge Domains //arXiv preprint arXiv:2502.09089. – 2025.

Rahman M. D. E-commerce Evolution: A Strategic Analysis of Alibaba's Business Ecosystem //Available at SSRN 5109165. – 2024.

Xie Yuying. On Alibaba's Marketing Strategy / Xie Yuying // Economy and Society. - 2022. - No. 6-1 (97). - P. 912-919. - EDN LZCMYY.

Yang, L., Cui, Y., Xuan, Y., et al. Personalized Embedding-based e-Commerce Recommendations at eBay. arXiv preprint arXiv:2102.06156, 2021. URL: https://arxiv.org/abs/2102.06156

Wang, Y., Guo, X., & Li, Y. Semantic Ads Retrieval at Walmart eCommerce with Language Models Progressively Trained on Multiple Knowledge Domains. arXiv preprint arXiv:2502.09089, 2025. URL: https://arxiv.org/abs/2502.09089

Lyskov, A. S., Lyamin, N. E., Kleshchuk, A. I., & Mamonova, E. A. (2024, August 21). Ranking with personalization in fashion-ecom: architecture, methods, experiments. Habr. Retrieved October 2, 2025, from https://habr.com/ru/companies/lamoda/articles/840370/

Luo C. et al. Exploring Query Understanding for Amazon Product Search //2024 IEEE International Conference on Big Data (BigData). – IEEE, 2024. – С. 2343-2348.

Google Shopping Case Studies. Think with Google. URL: https://www.thinkwithgoogle.com/collections/shopping-case-studies/ (date of access: 02.10.2025).

These 11 Stores Are Killing It On Google Shopping (Case Studies). Store Growers. 2023. URL: https://www.storegrowers.com/google-shopping-case-studies/ (date of access: 02.10.2025).


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность ИТ конгресс СНЭ

ISSN: 2307-8162