From Traditional Keyword Search to AI-Powered Search: Our Journey

“In January 2024, we launched our in house search solution, transitioning away from third-party providers to gain greater control over relevance, performance, and innovation. Our initial focus was identifier search, ensuring customers could quickly find products using SKUs, part numbers, and other structured identifiers.

With this foundation in place, we began our journey toward AI-powered search to enhance recall and relevance for more complex queries. We integrated AI-driven reranking for head terms, leveraging machine learning to reorder results based on behavioral signals. Recognizing the limitations of strict lexical matching, we introduced semantic expansion using synonym models, improving query understanding and recall.

To enhance the search experience further, we built a typeahead model, making real-time query suggestions more intuitive and personalized. As our AI capabilities matured, we implemented KNN search, enabling vector-based retrieval to surface results that go beyond traditional term matching. To fine-tune ranking, we introduced Learning to Rank (LTR), optimizing results based on click-through rates and conversion signals.

Our journey from standing up our first traditional keyword search solution to AI-powered retrieval has transformed our search experience, but it hasn’t been without challenges. We’ll share key lessons from this evolution—balancing precision vs. recall, managing infrastructure complexity, and evaluating AI-driven improvements. This session will provide a practical roadmap for search teams looking to transition from keyword-based search to AI-enhanced discovery in an eCommerce setting.”

Jon Vivers

Zoro

Jon Vivers, Senior Technical Product Manager for Search at Zoro.com, specializes in AI-driven search, enhancing product discovery in the tools and business supplies industry. He has launched multiple AI-powered search solutions, leveraging machine learning, NLP, and data-driven decision-making to integrate search seamlessly into business operations.

Jason Taylor

Zoro

Jason Taylor is Lead Data Scientist at Zoro, where he leads the Search Ranking and Retrieval pod and specializes in developing Machine Learning-based solutions for search and applying Generative AI to address product data and operational efficiency challenges. He has over 13 years of experience applying NLP to build large-scale solutions across several domains, including Healthcare, Defense, and E-Commerce.

Meet Parekh

Zoro

Meet Parekh is a Search and AI Specialist with expertise in e-commerce search, retrieval systems, vector search, LTR models & Personalisation. Currently at Zoro, he spearheads the initiatives to optimize search and discovery, enhancing product findability and customer experience. Previously at CB Insights, he played a key role in Search, ETL Pipelines, while also contributing to initial PoCs of ChatCBI and CBI Super Analyst - AI Powered agents that transformed business intelligence and data driven decision making.