Int'l Conference on Predictive APIs: RTB Optimizer presentation
?Download as PPT, PDF?
4 likes?3,649 views
Real-time bidding, in the context of digital marketing, refers to the purchase of advertising impressions one at a time, responding to tens of thousands of messages per second, paying a different price for each via an auction mechanism. This talk will cover in detail how Datacratic¨s RTB Optimizer Prediction API predicts the outcome of buying a given impression, then computes the economic value of that outcome to produce optimal bidding behaviour.
![Second price auctions
? First Price Auctions
C You bid $1, I bid $2: I win, and I pay $2
? RTB uses Second Price Auctions
C You bid $1, I bid $2: I win, and I pay $1
? Optimal bid = E[ value ]
C Say it¨s worth $2 to me
C I will never bid more than $2
C If I bid $1.50 and you bid $1.75: I¨ve lost an opportunity for $0.25 surplus!
C I should always bid $2](https://image.slidesharecdn.com/nicolaskruchtenpapis2013-141118055653-conversion-gate01/85/Int-l-Conference-on-Predictive-APIs-RTB-Optimizer-presentation-11-320.jpg)
![Don¨t buy lottery tickets!
E[ value ] = payout * P( getting the payout )](https://image.slidesharecdn.com/nicolaskruchtenpapis2013-141118055653-conversion-gate01/85/Int-l-Conference-on-Predictive-APIs-RTB-Optimizer-presentation-12-320.jpg)
![What¨s it to you?
? If client gets paid $10,000 for 1,000 then payout = $10
E[ value | bid-request ] = $10 * P( conversion | bid-request )
? What was an economics problem is now a prediction
problem
? We need to calibrate to predict true probabilities](https://image.slidesharecdn.com/nicolaskruchtenpapis2013-141118055653-conversion-gate01/85/Int-l-Conference-on-Predictive-APIs-RTB-Optimizer-presentation-13-320.jpg)
![RTB Optimizer
Bids API
E[ value ]
Outcomes
API
P( outcome )](https://image.slidesharecdn.com/nicolaskruchtenpapis2013-141118055653-conversion-gate01/85/Int-l-Conference-on-Predictive-APIs-RTB-Optimizer-presentation-14-320.jpg)
![Collecting the data
? To compute P( X | Y ) we need examples of Y¨s with an X label
? RTB Optimizer uses mix of strategies to meet campaign goals
? Probe strategy bids randomly to collect data
? Optimized strategy bids with E[ value]
? Automatic training/retraining when API see enough examples](https://image.slidesharecdn.com/nicolaskruchtenpapis2013-141118055653-conversion-gate01/85/Int-l-Conference-on-Predictive-APIs-RTB-Optimizer-presentation-15-320.jpg)
![RTB Optimizer
Bids API
Probe
E[ value ]
Outcomes
Training
API
P( outcome )](https://image.slidesharecdn.com/nicolaskruchtenpapis2013-141118055653-conversion-gate01/85/Int-l-Conference-on-Predictive-APIs-RTB-Optimizer-presentation-16-320.jpg)
![RTB Optimizer
Bids API
Probe
Real-Time
Stats
Tables
E[ value ]
Outcomes
Training
API
GLZ Classifier
Batch](https://image.slidesharecdn.com/nicolaskruchtenpapis2013-141118055653-conversion-gate01/85/Int-l-Conference-on-Predictive-APIs-RTB-Optimizer-presentation-20-320.jpg)
Int'l Conference on Predictive APIs: RTB Optimizer presentation
- 1. REAL TIME MACHINE LEARNING DECISIONS AS A SERVICE RTB Optimizer: Behind the scenes with a Predictive API Nicolas Kruchten PAPIs.io C November 18, 2014
- 2. About Datacratic ? Software company specializing in high performance systems and machine learning ? 30 employees, founded in 2009, based in Montr└al, Qu└bec, Canada with an office in New York ? 3 Predictive APIs in market today ? Building a Machine Learning Database to help others build Predictive APIs and Apps
- 3. Real-Time Bidding for online advertising Real-Time Exchange Bidder Bidder Bidder Bidder Web Browser GET ad bid requests
- 4. Real-Time Bidding for online advertising Real-Time Exchange Bidder Bidder Bidder Bidder Web Browser ad bids auction
- 5. Real-Time Bidding for online advertising Real-Time Exchange Bidder Bidder Bidder Bidder Web Browser ad bids auction This happens millions of times per second Bidders must respond within 100 milliseconds
- 6. Real-Time Bidding for online advertising Real-Time Exchange Bidder Bidder Bidder Bidder Web Browser ad bids auction RTB Optimizer enables bidders to achieve campaign goals
- 7. Campaign goals ? Advertising campaigns are typically outcome-oriented C Clicks C Video views C Conversions: app installs, purchases, sign-ups ? e.g. Ad network has sold someone 1,000 outcomes for $1,000 ? e.g. Advertiser has $1,000 to get as many outcomes as possible ? Essentially maximize profit or minimize cost-per-outcome
- 8. Datacratic¨s RTB Optimizer ? Client bidder relays bid-requests to API, API tells it how to bid ? Handles 100,000 queries per second, for 100s of campaign ? API says which campaign should bid and how much ? API also needs outcomes in real-time and campaign goals
- 9. RTB Optimizer Bids API Outcomes API
- 10. A Predictive API that learns ? Datacratic has no proprietary data set ? API can learn from scratch from the bid-request stream what works for each campaign: C Contextual features: website, time of day, banner size and placement C User features: geo-location, browser, language, # of impressions shown C Customer-provided data: about the user, about the website ? Provides insights into what features are driving performance ? Can re-use learnings from previous campaigns
- 11. Second price auctions ? First Price Auctions C You bid $1, I bid $2: I win, and I pay $2 ? RTB uses Second Price Auctions C You bid $1, I bid $2: I win, and I pay $1 ? Optimal bid = E[ value ] C Say it¨s worth $2 to me C I will never bid more than $2 C If I bid $1.50 and you bid $1.75: I¨ve lost an opportunity for $0.25 surplus! C I should always bid $2
- 12. Don¨t buy lottery tickets! E[ value ] = payout * P( getting the payout )
- 13. What¨s it to you? ? If client gets paid $10,000 for 1,000 then payout = $10 E[ value | bid-request ] = $10 * P( conversion | bid-request ) ? What was an economics problem is now a prediction problem ? We need to calibrate to predict true probabilities
- 14. RTB Optimizer Bids API E[ value ] Outcomes API P( outcome )
- 15. Collecting the data ? To compute P( X | Y ) we need examples of Y¨s with an X label ? RTB Optimizer uses mix of strategies to meet campaign goals ? Probe strategy bids randomly to collect data ? Optimized strategy bids with E[ value] ? Automatic training/retraining when API see enough examples
- 16. RTB Optimizer Bids API Probe E[ value ] Outcomes Training API P( outcome )
- 17. Bias control ? Never stop the probe strategy ? Always need control group for evaluation, retraining ? Risk of filter bubbles: future models trained on previous output ? Bid requests are randomly routed to probe, less often over time ? Models automatically back-tested before deployment
- 18. How to learn in real-time ? Classify using bagged generalized linear models ? Generate non-linear features with statistics tables ? Periodically retrain classifier ? Continuously update stats tables
- 19. Statistics Table by example Table Bucket Impressions Outcomes Outcomes/I mpressions 95% Confidence Lower Bound on Outcomes/Impressi ons Browser Chrome 5M 3k 0.060% 0.058% Firefox 3M 1k 0.033% 0.031% Website abc.com 4M 2k 0.050% 0.048% xyz.com 1k 10 1.000% 0.481%
- 20. RTB Optimizer Bids API Probe Real-Time Stats Tables E[ value ] Outcomes Training API GLZ Classifier Batch
- 21. Implementation details (are everything) ? 100k requests per second, 10 millisecond latency, running 24/7, 1 trillion predictions to date ? Distributed system, written in C++ 11 ? AWS: data in S3, training runs on Amazon EC2 spot market ? http://opensource.datacratic.com/ C RTBkit C JML C StarCluster
- 22. Does it work? Classification success? ROC or calibration curves´
- 23. Does it work? Classification success? ROC and calibration curves´ Optimization success? 80% reductions in cost-per-outcome´
- 24. Does it work? Classification success? ROC or calibration curves´ Optimization success? 80% reductions in cost-per-outcome´ Customer success! 25% monthly growth
- 25. REAL TIME MACHINE LEARNING DECISIONS AS A SERVICE Thanks! nicolas@datacratic.com