A user types black clutch into your search engine. Do they mean the handbag, the automobile part, or something else entirely?
Search is about matching the intent of the user with the information they need. For decades, relevance in information retrieval systems has meant things like BM25, TFIDF, field boosting, document boosting, etc. These simple heuristics & strategies have served us well, but ultimately fall short because they fail to semantically model intent. Our systems dont actually understand what users want, they just hope a few magic numbers will get us close enough.
Query Understanding is about using real intelligence to put users first. In this session, well talk about what Query Understanding is, why its important, & some practical strategies for making your search experience smarter.
Giovanni Fernandez-Kincade has been working with data, architecting systems, & leading teams of engineers for over a decade. Hes currently co-founder at Related Works, a problem-solving product studio & consultancy focused on the intersection of data, design, & search. At Etsy he was a Staff Software Engineer that lead the Search Ranking Team, which was responsible for the effectiveness & fairness of Etsys core search algorithm, & previously lead the Search Experience Team which worked on the entire Search user experience. He's focused on Search from the ground up: infrastructure, ranking & machine-learned relevance, diversity, fairness, autosuggest, faceting, navigation, taxonomy, mobile, experimentation, etc. Prior to working at Etsy, Gio worked at CapitalIQ where he designed, built, & maintained a multi-terabyte database, real-time processing-system, & search engine for globally-sourced financial reports. On weekends & early weekday mornings you can find him surfing in sunny Rockaway Beach, NY.