Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Recommending and searching @ Spotify


Published on

These are the slides I used for my talk at the BIG Track at the Web Conference 2019. This is a very similar talk to what I gave at the celebration kickoff of Chalmers AI Research Centre in Gothenburg in March 2019. It has a bit more and reflect some of the most recent work we are doing at Spotify Research. I am posted these again as people are asking for the slides. Thank you.

Published in: Internet

Recommending and searching @ Spotify

  1. 1. Recommending and Searching Research @ Spotify Mounia Lalmas May 2019
  2. 2. What we do at Spotify
  3. 3. Spotify’s mission is to unlock the potential of human creativity — by giving a million creative artists the opportunity to live off their art and billions of fans the opportunity to enjoy and be inspired by it.
  4. 4. Our team mission: Match fans and artists in a personal and relevant way. ARTISTS FANS
  5. 5. What does it mean to match fans and artists in a personal and relevant way?
  6. 6. songs playlists podcasts ... catalog search browse talk users What does it mean to match fans and artists in a personal and relevant way?Artists Fans
  7. 7. “We conclude that information retrieval and information filtering are indeed two sides of the same coin. They work together to help people get the information needed to perform their tasks.” Information filtering and information retrieval: Two sides of the same coin? NJ Belkin & WB Croft, Communications of the ACM, 1992.
  8. 8. “We can conclude that recommender systems and search are also two sides of the same coin at Spotify. They work together to help fans get the music they will enjoy listening”. PULL PARADIGM PUSH PARADIGM is this the case?
  9. 9. Home … the push paradigm
  10. 10. Home Home is the default screen of the mobile app for all Spotify users worldwide. It surfaces the best of what Spotify has to offer, for every situation, personalized playlists, new releases, old favorites, and undiscovered gems. Help users find something they are going to enjoy listening to, quickly.
  11. 11. Streaming UserBaRT Explore, Exploit, Explain: Personalizing Explainable Recommendations with Bandits. J McInerney, B Lacker, S Hansen, K Higley, H.Bouchard, A Gruson & R Mehrotra, RecSys 2018. BaRT: Machine learning algorithm for Spotify Home
  12. 12. BaRT (Bandits for Recommendations as Treatments) How to rank playlists (cards) in each shelf first, and then how to rank the shelves?
  13. 13. Explore vs Exploit Flip a coin with given probability of tail If head, pick best card in M according to predicted reward r → EXPLOIT If tail, pick card from M at random → EXPLORE BaRT: Multi-armed bandit algorithm for Home
  14. 14. Success is captured by the reward function Reward Binarised Streaming Time BaRT UserStreaming success is when user streams the playlist for at least 30s
  15. 15. Is success the same for all playlists? Consumption time of a sleep playlist is longer than average playlist consumption time. Jazz listeners consume Jazz and other playlists for longer period than average users.
  16. 16. one reward function for all users and all playlists success independent of user and playlist one reward function per user x playlist success depends on user and playlist too granular, sparse, noisy, costly to generate & maintain one reward function per group of users x playlists success depends on group of users listening to group of playlists Personalizing the reward function for BaRT
  17. 17. Co-clustering using streaming time users playlists user groups playlist groups Dhillon, Mallela & Modha, "Information-theoretic co-clustering”, KDD 2003. group = cluster group of user x playlist = co-cluster
  18. 18. user type playlist type
  19. 19. Deriving User- and Content-specific Rewards for Contextual Bandits. P Dragone, R Mehrotra & M Lalmas. WWW 2019. Using playlist consumption time to inform metric to optimise for (Home reward function) Optimizing for mean consumption time led to +22.24% in predicted stream rate. Defining per user x playlist cluster led to further +13%. mean of consumption time co-clustering user group x playlist type Metrics importance to affinity type features over generic (age/day) features
  20. 20. Jointly Leveraging Intent and Interaction Signals to Predict User Satisfaction with Slate Recommendations. R Mehrotra, M Lalmas, D Kenney, T Lim-Meng & G Hashemian. WWW 2019. Three Intent Models intent important to interpret user interaction Passively Listening - quickly access playlists or saved music - play music matching mood or activity - find music to play in background Actively Engaging - discover new music to listen to now - save new music or follow new playlists for later - explore artists or albums more deeply User intent Machine learning across intents on Home is better than intent-agnostic machine learning Considering intent improves ability to infer user satisfaction by 20%.
  21. 21. Towards a Fair Marketplace: Counterfactual Evaluation of the trade-off between Relevance, Fairness & Satisfaction in Recommendation Systems. R Mehrotra, J McInerney, H Bouchard, M Lalmas & F Diaz. CIKM 2018. Playlist is deemed diverse if it contains tracks from artists with different popularity groups. Very few sets have both high relevance & high diversity. Diversity Relevance Diversity Recommender system optimizing for relevance may not have high diversity estimate. Gains in fairness possible without severe loss of satisfaction. Adaptive policies aware of user receptiveness perform better.
  22. 22. Offline evaluation framework to launch, evaluate and archive machine learning studies, ensuring reproducibility and allowing sharing across teams. Offline Evaluation to Make Decisions About Playlist Recommendation Algorithms. A Gruson, P Chandar, C Charbuillet, J McInerney, S Hansen, D Tardieu & B Carterette, WSDM 2019. Offline evaluation
  23. 23. Search … pull paradigm
  24. 24. Large catalog 40M+ songs, 3B+ playlists 2K+ microgenres Many languages 79 markets Different modalities Typed, voice Heterogeneous content Music, podcast Various granularities Song, artist, playlist, podcast Various goals Focus, discover, lean-back, mood, activity Searching for music
  25. 25. Overview of the user journey in search TYPE/TALK User communicates with us CONSIDER User evaluates what we show them DECIDE User ends the search session INTENT What the user wants to do MINDSET How the user thinks about results
  26. 26. Search is instantaneous … at each keystroke m my my_ my_f my_fav
  27. 27. s sa satt sat sati statis Search is instantaneous … the search logs for “satisfaction” From prefix to query → What is the actual query? → What is a click vs prefix vs query? prefix query
  28. 28. A user can approach any intent with any mindset FOCUSED One specific thing in mind OPEN A seed of an idea in mind EXPLORATORY A path to explore LISTEN Have a listening session ORGANIZE Curate for future listening SHARE Connect with friends FACT CHECK Find specific information EXPLORATORY mindset seems rare and likely better served by other features such as Browse. LISTEN and ORGANIZE are most prominent intents & associated with lean-back vs lean-in behavior.
  29. 29. FOCUSED One specific thing in mind OPEN A seed of an idea in mind EXPLORATORY A path to explore ● Find it or not ● Quickest/easiest path to results is important ● From nothing good enough, good enough to better than good enough ● Willing to try things out ● But still want to fulfil their intent ● Difficult for users to assess how it went ● May be able to answer in relative terms ● Users expect to be active when in an exploratory mindset ● Effort is expected User mindsets Just Give Me What I Want: How People Use and Evaluate Music Search. C Hosey, L Vujović, B St. Thomas, J Garcia-Gathright & J Thom, CHI 2019. How the user thinks about results
  30. 30. Focused mindset Search Mindsets: Understanding Focused and Non-Focused Information Seeking in Music Search. A Li, J Thom, P Ravichandran, C Hosey, B St. Thomas & J Garcia-Gathright, WWW 2019. Understanding mindset helps us understand search satisfaction. 65% of searches were focused. When users search with a Focused Mindset Put MORE effort in search. Scroll down and click on lower rank results. Click MORE on album/track/artist and LESS on playlist. MORE likely to save/add but LESS likely to stream directly.
  31. 31. Developing Evaluation Metrics for Instant Search Using Mixed Methods. P Ravichandran, J Garcia-Gathright, C Hosey, B St. Thomas & J Thom. SIGIR 2019. success rate more sensitive than click-through rate. Metrics Users evaluate their experience on search based on two main factors: success and effort TYPE User communicates with us CONSIDER User evaluates what we show them DECIDE User ends the search session EFFORT SUCCESS
  32. 32. Voice … the pull & push paradigm?
  33. 33. Search by voice Users ask for Spotify to play music, without saying what they would like to hear → open mindset Play Spotify Play music Play music from Spotify Play me some music Play the music Play my Spotify Play some music on Spotify Play some music Play music on Spotify
  34. 34. Non-specific querying is a way for a user to effortlessly start a listening session via voice. Non-specific querying is a way to remove the burden of choice when a user is open to lean-back listening. User education matters as users will not engage in a use-case they do not know about. Trust and control are central to a positive experience. Users need to trust the system enough to try it out. Search as push paradigmSearch by voice
  35. 35. Some final words
  36. 36. Qualitative&quantitativeresearch KPIs&businessmetrics Algorithms Training & Datasets Optimizationmetrics Evaluation offline & online Measurement & signals Features (item) Features (user) Features (context) Bias Making machine learning work … at Spotify
  37. 37. Qualitative&quantitativeresearch KPIs&businessmetrics Algorithms Training & Datasets Optimizationmetrics Evaluation offline & online Measurement & signals Features (item) Features (user) Features (context) Bias Making machine learning work … in this talk conversational search (voice) intent & mindset BaRT rewardfunction forBaRT diversity ML-Lab search metrics
  38. 38. Thank you!