Staff Software Engineer
The Home Depot
Jared Moore is an engineer on the Search team at The Home Depot working on almost every different piece of the search experience over the past 3.5 years. He has a Bachelor’s Degree in Computer Science and is currently pursuing a Master’s in Machine Learning, both from Georgia Tech.
Jared Moore is speaking at the following session/s
Overcoming the Challenges of Query Autocomplete
Query Autocomplete provides many on-going challenges that need regular consideration, from striking a balance between the goals of best understanding user intent and driving revenue to provide the best possible results to our customers by providing relevant, unambiguous search terms, constant analysis and refinement are required to meet the challenges we face in providing our customers the best search experience.
We wish to discuss the past year of improvements to our Query Autocomplete service, including phonetic, semantic, and order-insensitive deduplication of terms, normalization of noisy data in our search terms, and identifying and removing otherwise good search terms that don’t make sense in the context of our catalog. We also intend to discuss the metrics where these changes demonstrate improvement and discuss the next steps for improving the Autocomplete experience for our users.
We hope that the audience will gain an understanding of how we overcame several challenges with working with Customer Behavior data and be able to apply the lessons we learned to their own data processes.
Developers and Data Scientists who work with customer behavior and search data.