Machine learning and data at Meetup
4 likes797 views
This document provides an overview of machine learning and data recommendations at Meetup.com. It discusses how Meetup uses machine learning models like logistic regression and collaborative filtering to provide topic and group recommendations to users based on their location, interests, and other attributes. Features are engineered using data like topic matches, Facebook friends, and distances between locations. Challenges include cold starts, sparsity of data, and cleaning issues. Future work may include recommendations based on clicks and impressions as well as people-to-people recommendations.
Machine learning and data at Meetup
- 1. Machine Learning and Data at Meetup Evan Estola Meetup.com evan@meetup.com @estola
- 2. My Background Software Engineer/Data Scientist Machine learning team At Meetup since May 2012 BS Computer Science Information Retrieval Data Mining Math Linear Algebra Graph Theory
- 3. You Data Scientists? Engineers? Statisticians? Students? Non-technical?
- 4. What this talk is Super secret peek into Meetup! Meetup recommendations examples How we do recommendations (model/features) Lessons learned/whats next
- 5. What this talk isnt What is a data scientist? What is big data? How does matrix factorization or gradient boosted decision trees or map reduce or this framework I hope youll use work?
- 6. Why Meetup data is cool Real people meeting up Every meetup could change someone's life No ads, just do the best thing Oh and 114 million rsvps by >14 million members 2.7 million rsvps in the last 30 days ~1/second
- 8. Data at Meetup User data Site monitoring/performance AB testing Recommendations*
- 9. Everything is a recommendation Not my phrase Not actually true yet Working on it
- 10. Recommendation
- 13. Topic Recommendations New registrant Dont know anything about you yet! Most popular is boring/repetitive Algorithm: Group local meetups by topic Select topic with most groups Remove those groups Repeat
- 16. Group/Event Recommendations Replaced a topic only system Inputs: Member, location, topics, facebook friends? demographics? Outputs: Ranking
- 17. Collaborative Filtering Classic recommendations approach Users who like this also like this
- 18. Why Recs at Meetup are hard Incomplete Data (topics) Cold start Asking user for data is hard Going to meetups is scary Sparsity Location Groups/person Membership: 0.001% Compare to Netflix: 1%
- 19. Supervised Learning/Classification Inferring a function from labeled training data Joined Meetup/Didnt join Meetup Features
- 20. Topic Match
- 21. State Match
- 22. Logistic Regression Score Probability Ranking Fast + Easy Weights!
- 23. Group recommendation weights TopicMatch 1.21 TopicMatchExtended 0.17 FacebookFriends 0.15 SecondDegreeFacebook 0.79 AgeUnmatch -2.20 GenderUnmatch -2.6 StateMatchFeature 0.44 CityMatch 0.02 DistanceBucket <2 1.39 DistanceBucket 2-5 0.83 DistanceBucket 5-10 0.60 DistanceBucket >10 n/a
- 24. Making up features Zipscore All topics not created equal Facebook likes
- 25. Real data is gross Preprocessing is critical! missing data outliers log scale bucketing selection/sampling (not introducing bias)
- 26. Cleaning data Schenectady Beverly Hills Astronaut Fake RSVP boosts (+100 guests!) Rsvp hogs
- 29. TO THE FUTURE! Hadoop Clicks Impressions People to people recommendations? Recommending people to groups?
- 30. Thanks! Smart people come work with me. http://www.meetup.com/jobs/ Special thanks: Chris Halpert Victor J Wang