Context sensitive autocomplete suggestions using LSTM and Pair-wise learning

Dileep Kumar Patchigolla and Minohar Sripada • Location: Theater 4 • Back to Haystack 2020

Autocomplete is a predominant feature in e-commerce search. By being relevant, Autocomplete should help users quickly find the query they intended to type with minimal keystrokes. This talk presents an approach on how this is achieved by considering the users context as a signal for re-ranking the query suggestions. A user context is based on a diverse sequence of events - searches, product interactions, category browse etc. It is generated using an LSTM model that is optimized by using pairwise ranking of queries. This context is extracted in real-time & fed into the Autocomplete model which re-ranks suggestions accordingly.

Watch the Video

Dileep Kumar Patchigolla


Dileep leads the Data Science efforts in Search team at Target. Primarily, he has worked on revamping the typeahead suggestions, synonym mining, and spellcheck models to improve search experience on Target’s website. Prior to his current role, he has 10 years of experience solving problems using data science across various industries - friend recommendations & content ranking in social networking, user segmentation & marketing campaign optimization in mobile games, and supply prediction in commodity markets. His primary interest lies in utilizing data science and machine learning to improve customer experiences. Along with his regular job, he is also pursuing his MS in Analytics from Georgia Institute of Technology, Atlanta and is expected to graduate in 2020.

Minohar Sripada


Manohar is a Senior Engineering Manager in Search team at Target, where he leads a team to improve Search relevancy. Currently, he is focussed on contextualisation of Search & improving Typeahead relevancy. Manohar has contributed in bringing state of art experience in various Search areas like Facets, Null & Low Recovery, Related Searches etc. Apart from Search, he is also responsible for leading efforts in applying NLP & Ranking on Product Reviews that is seen at Target’s website. Prior to Target, he has 12 years of experience in delivery of large scale applications at Oracle & IBM.