Beat Google (Ads)'s bidder using ML
•Download as PPTX, PDF•
0 likes•103 views
This document summarizes the results of an A/B test comparing the bidding performance of Dolead's machine learning bidder to Google's bidder on 50 paid search campaigns over 4 weeks. The Dolead bidder was able to stay below the target cost-per-acquisition (CPA) 63% of the time compared to 33% for Google. While Google had more conversions in 67% of campaigns, the Dolead bidder achieved conversions at a lower CPA in 83% of campaigns. As a result, Dolead's margin was 35% higher than Google's margin overall.
Recommended
More Related Content
Similar to Beat Google (Ads)'s bidder using ML
Similar to Beat Google (Ads)'s bidder using ML (19)
Recently uploaded
Recently uploaded (20)
Beat Google (Ads)'s bidder using ML
- 1. DOLEAD @ Py.Paris –NOV 2018 WWW.DOLEAD.COM Beat Google’s bidder using ML Dolead RD team Arnaud Fouchet PyApéro #1 13.12.2018
- 2. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 2 Paid search basics
- 3. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 3 Paid search basics
- 4. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 4 Paid search basics Click
- 5. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 5 Paid search basics Click Visit Landing page
- 6. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 6 Paid search basics Click Visit Landing page Subscription (victory) Not interested (defeat)
- 7. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 7 Paid search basics Typed: “BTS a distance” Will he click ? Will he subscribe ? New user Impression Click Subscription
- 8. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 8 Paid search basics Typed: “BTS a distance” Will he click ? Will he subscribe ? New user Impression Click Subscription 100$ question : how much should I pay the ad ?
- 9. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 9 Paid search basics Typed: “BTS a distance” Will he click ? Will he subscribe ? New user Impression Click Subscription 100$ question : how much should I pay the ad ? Google’s problem
- 10. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 10 Paid search basics Typed: “BTS a distance” Will he click ? Will he subscribe ? New user Impression Click Subscription 10$ question : how much should I pay the click ? Google’s problem
- 11. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 11 Paid search basics How much should I pay the click ? 1. Find revenue by click
- 12. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 12 Paid search basics How much should I pay the click ? 1. Find revenue by click 1. Pay less than that
- 13. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 13 Paid search basics How much should I pay the click ? 1. Find revenue by click (using Machine learning: search query → revenue by click) 1. Pay less than that
- 14. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 14 Paid search basics Typed: “BTS a distance” Will he click ? Will he subscribe ? New user Impression Click Subscription 10$ question : how much should I pay the click ? Google’s problem Google’s bidder
- 15. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 15 Paid search basics Typed: “BTS a distance” Will he click ? Will he subscribe ? New user Impression Click Subscription 1$ for 2 questions : Do I accept giving Google all power ? Can we do better ? Google’s problem Google’s bidder
- 16. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 16 Paid search basics Typed: “BTS a distance” Will he click ? Will he convert ? New user CPA: Cost Per Acquisition (Cost of a conversion) Impression Click Conversion 1$ for 2 questions : Do I accept giving Google all power ? Can we do better ? Google’s problem Google’s bidder
- 17. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 17 Our ML research
- 18. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 18 Our ML research
- 19. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 19 Our ML research
- 20. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 20 Consensus RF GBDT Log Reg ...
- 21. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 21 Our ML research
- 22. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 22 Neural networks
- 23. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 23 Paid search basics Typed: “BTS a distance” Will he click ? Will he convert ? New user Impression Click Conversion 10$ question : how much should I pay the click ? Google’s problem
- 24. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 24 Our ML research
- 25. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 25 Paid search basics Typed: “BTS a distance” Will he click ? Will he convert ? New user Impression Click Conversion 10$ question : how much should I pay the click ? Google’s problem
- 26. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 26 Our ML research
- 27. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 27 Our ML research
- 28. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 28 Consensus RF GBDT NN ... Better
- 29. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 29 Consensus RF GBDT NN ... Better a x RF b x GBDT c x NN ... Weighted Consensus
- 30. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 30 Consensus RF GBDT NN ... Better a x RF b x GBDT c x NN ... Weighted Consensus RF GBDT NN ... Learned model f
- 31. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 31 Stacked models x RF NN GBDT ... x’ Learning problem on (x’, y)
- 32. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 32 Stacked models x RF NN GBDT ... x’ Learning problem on (x’, y) ➝ data leakage problem Train
- 33. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 33 Stacked models x RF NN GBDT DEVIL x’ Learning problem on (x’, y) ➝ data leakage problem Train
- 34. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 34 Measure Stacked Models PerfCampaign1 Train Test Predictions RF NN GBDT ... Campaign2 Train Test Predictions RF NN GBDT ... Campaign...
- 35. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 35 Measure Stacked Models PerfCampaign1 Train Test Predictions RF NN GBDT ... Campaign2 Train Test Predictions RF NN GBDT ... Campaign... CampaignT+1 Train Test Predictions RF NN GBDT ... CampaignT+2 Train Test Predictions RF NN GBDT ... CampaignT+... Test !
- 36. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 36 Our ML research
- 37. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 37 Bidder comparison: context A/B test Campaign Experiment 1: 50% bids Google Experiment 2: 50% bids Dolead
- 38. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 38 Bidder comparison: context A/B test 50 campaigns 4 weeks Goal : maximize conversions while respecting target CPA Campaign Experiment 1: 50% bids Google Experiment 2: 50% bids Dolead
- 39. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 39 Bidder comparison: % Below target CPA Raw results : - Google 33% - Dolead 63% Distribution CPA(Google) / target CPA CPA(Dolead) / target CPA
- 40. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 40 Bidder comparison: Conversions & CPA Conversions : In 67% of campaigns, Google had more convs Distribution Convs(Google) / Convs(Dolead)
- 41. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 41 Bidder comparison: Conversions & CPA Conversions : In 67% of campaigns, Google had more convs Distribution CPA : In 83% of campaigns, Dolead was cheaper Distribution Convs(Google) / Convs(Dolead) CPA(Google) / CPA(Dolead)
- 42. DOLEAD @ Py.Paris - NOV 2018 WWW.DOLEAD.COM 42 Bidder comparison: Conversions & CPA Conversions : In 67% of campaigns, Google had more convs Distribution Google’s margin: 9.8K CPA : In 83% of campaigns, Dolead was cheaper Distribution Dolead’s margin: 13.3K (~+35%) Convs(Google) / Convs(Dolead) CPA(Dolead) / CPA(Google)
- 43. DOLEAD @ Py.Paris –NOV 2018 WWW.DOLEAD.COM Thanks for your attention ! PyApero 13 décember 2018 www.pyapero.com