Ticketmaster datascience
•
4 likes•1,837 views
How Ticketmaster and Live Nation - makes live event recommendations - helps artists understand and grow their audience - fights ticket scalpers with machine learning
Recommended
More Related Content
Recently uploaded
Recently uploaded (20)
Featured
Featured (20)
Ticketmaster datascience
- 1. Fans just wanna have fun! @petricek
- 2. Every year: hundreds of millions tickets sold worth Billions of Dollars
- 10. ! Recommendations! ! Who are my fans? !
- 11. ! Recommendations! ! Who are my fans? !
- 12. ! Tickets to the Fans! (not scalpers)! ! Recommendations! ! Who are my fans? !
- 13. ! Tickets to the Fans! (not scalpers)! ! Recommendations! ! Who are my fans? !
- 14. Quality evaluation Data collection Recommendation Strategies
- 15. Quality evaluation Data collection Recommendation Strategies
- 19. 1px 1px“pixel”
- 28. Number of requests over time
- 29. Number of requests over time something big went on sale
- 30. Number of requests over time something big went on sale ~10 x
- 31. Quality evaluation Data collection Recommendation Strategies
- 32. Quality evaluation Data collection Recommendation Strategies
- 33. Ticket Alert
- 46. Top Sellers Offline aggregate over many days
- 47. Hot right now 30min sliding window
- 48. Hot right now 30min sliding window count rank “hot right now”filter
- 49. After viewing fans eventually bought
- 58. Ticket! Availability ! Service Event Feed Recommender! Service Pixel! Service 100ms SLA async Storm
- 65. Quality
- 66. Expert feedback
- 71. Availability
- 72. A/B testing
- 73. Stealth testing
- 74. hdfs bolt
- 82. Quality evaluation Data collection Recommendation Strategies
- 84. Contextual bandits Exploration v Exploitation Next steps
- 85. Contextual bandits Exploration v Exploitation More context (user, artist, venue, event metadata) Next steps
- 86. ! Tickets to the Fans! (not scalpers)! ! Recommendations! ! Who are my fans? !
- 87. ! Tickets to the Fans! (not scalpers)! ! Recommendations! ! Who are my fans? !
- 93. $$$ $$$ $ $
- 94. $$$ $$$ $ $
- 95. $$$ $$$ $ $
- 96. $$$ $$$ $ $
- 102. HLL $$$HLL HLL
- 103. HLL $$$HLL HLL
- 106. Unique female users —————————— Unique users total Unique users with family —————————— Unique users total Unique high income users ——————————— Unique users total $$$HLL = HLL HLL HLL HLL = = HLL
- 108. Chvrchs 15% Asian
- 109. Chvrchs 15% Asian K. Michelle 57% African American
- 110. Chvrchs 15% Asian K. Michelle 57% African American Ramon Ayala 92% Hispanic
- 111. Chvrchs 15% Asian K. Michelle 57% African American Ramon Ayala 92% Hispanic Tom Petty 96% Caucasian
- 112. Millennials Grits and Biscuits Gen X Depeche Mode Baby Boomers Chicago Musical
- 122. ! Tickets to the Fans! (not scalpers)! ! Recommendations! ! Who are my fans? !
- 123. ! Tickets to the Fans! (not scalpers)! ! Recommendations! ! Who are my fans? !
- 134. 0 500 1000 Price
- 135. 0 500 1000 Price
- 137. |+
- 138. |+
- 149. vw vw vw vw ?
- 150. vw vw vw vw ?
- 151. vw vw vw vw ?
- 152. vw vw vw vw ?
- 153. vw vw vw vw ?
- 155. Arms Race Next steps
- 156. ! Tickets to the Fans! (not scalpers)! ! Recommendations! ! Who are my fans? !
- 157. ! Tickets to the Fans! (not scalpers)! ! Recommendations! ! Who are my fans? !
- 158. ! Tickets to the Fans! (not scalpers)! ! Recommendations! ! Who are my fans? !
- 159. Now what?
- 160. Decades of granular and longitudinal data Now what?
- 161. Recommend the best Seat for you