Search & Recommendations

Search & recommendations research at Spotify focuses on identifying ways to provide users with seamless access to their favorite audio content, from music to podcasts, and to help them explore their taste. A big focus is on building highly effective, personalized and interactive models that exploit contextual information and historical user interactions. Our research interests include large-scale recommendation algorithms for music and more generally audio discovery, algorithms for audio search through voice and text, query analysis for effective query suggestion, query completion and search assistance, multilingual information retrieval for voice search, and ranking algorithm for revenue and music ads.

Latest Search & Recommendations Publications

April 2022 | The Web Conference (WWW)

Sequential Recommendation via Stochastic Self-Attention

Ziwei Fan, Zhiwei Liu, Alice Wang, Zahra Nazari, Lei Zheng, Hao Peng, Philip S. Yu

April 2022 | The Web Conference (WWW)

Using Survival Models to Estimate Long-Term Engagement in Online Experiments

Praveen Chandar, Brian St. Thomas, Lucas Maystre, Vijay Pappu, Roberto Sanchis-Ojeda, Tiffany Wu, Ben Carterette, Mounia Lalmas, Tony Jebara

April 2022 | The Web Conference (WWW)

Choice of Implicit Signal Matters: Accounting for User Aspirations in Podcast Recommendations

Zahra Nazari, Praveen Chandar, Ghazal Fazelnia, Catie Edrwards, Ben Carterette, Mounia Lalmas

Other Research Areas