際際滷

際際滷Share a Scribd company logo

Bullseyeupdated2

?Download as PPT, PDF?
?
Andrew Mager
Andrew Mager

The document discusses developing a predictive model for forecasting page views and ad impressions for Bullseye ad campaigns. It involves collecting data on games, predicting page views based on determinants like user activity and game quality, and finding the relationship between page views and ad impressions. The goal is to provide more objective predictions than existing methods to improve pricing and reduce under- or over-delivery of ad impressions.

1 of 17
Forecasting Page Views & Ad Impressions for Bullseye Ad Campaigns David Feng Statistical Analyst Intern GEL, Trax
What is Bullseye? Cross-game advertising A client¨s ad campaign runs exclusively on a selected game space for a set amount of time. Example I want to advertise for a new football game I created. I feel that Madden players would be interested in my game. I buy a Bullseye campaign on Madden NFL 09, since I am targetting Madden players.
Existing Bullseye Procedures Sales team has two options Propose a predicted number of ad impressions to the client (but how much?) Charge a flat rate on the Bullseye campaign (Halo 3 = Balls of Fury) Problems Under-delivery: must compensate client in some other way C make goods Over-delivery: lost opportunity for revenue Flat-rate pricing: lost opportunity for revenue on AAA games
Bullseye Q1¨07 Q2¨07 Q3¨07 Q4¨07 Q1¨08 Q2¨08 eCPM (censored) % of GS Revenue 9% 5% 4% 4% 3% 2%
The Bullseye Predictive Model Objective: To provide a more objective means for predicting the number of advertising impressions in a game space. 4 phases Data-collection and processing Predict number of page views for a game space 30 days, 60 days and 90 days in advance Find the relationship between page views and advertising impressions Test validity of models and develop business rules
The Bullseye Predictive Model Objective: To provide a more objective means for predicting the number of advertising impressions in a game space. 4 phases Data-collection and processing Predict number of page views for a game space 30 days, 60 days and 90 days in advance Find the relationship between page views and advertising impressions Test validity of models and develop business rules
I. Data Collection Gathered data on all games released from 1/1/06 to 5/31/08 using Trax Data pulled in Mon-Sun increments 3782 games, ~2700-2800 after removing irrelevant games Computed lifecycle data for all games on the weekly level
II: Predicting Page Views Predict page views because it should be the strongest determinant of ad impressions Determinants From Trax Users Page Views Searches Videos Served Total Users Tracking New Users Tracking Price Checks Forum Activity Pre-existing Awareness IP Type (Original, Sequel, Licensed) Milestones (News, Previews, Videos) Quality of Game Average Review Score (as a stand-in for preview score) Gamespot Traffic Quarter game is released
Heteroskedasticity: Big Games = Big Errors
Constructing the Forecast Interval Two sources of uncertainty Standard Error of Regression (SER) Coefficient Uncertainty SER Future is uncertain (see figure) Reduce through stratification (e.g. separate models for X360 games, casual games, Q4, high PV-growth) Coefficient Uncertainty Uncertain coefficients, so uncertain dependent variable Ignored Sample size not large enough Software limitation
Solution Sell Bullseye ad campaigns on at least 3 SKUs to reduce risk of underdelivery Just need to reduce the SER to improve models¨ goodness-of-fit
Summary of Results C 30 Days Platform Week0 Week1 Week2 Week-1 Month1 X360 PS3 Wii PC DS PSP
Summary of Results C 60 Days Platform Week0 Week1 Week2 Week-1 Month1 X360 PS3 Wii PC DS PSP
Summary of Results C 90 Days Platform Week0 Week1 Week2 Week-1 Month1 X360 PS3 Wii PC DS PSP
Testing Validity of Models Use games released after 5/31/08 Test Interface & Final Interface Interface will eventually be automated into a new tool, so that the sales rep only needs to put in the game ID, and all data will be pulled from Trax A new Bullseye tool and/or an internal version of Trax could be created to ease testing and usage of the models
Next Steps Test models Finalize relationship between page views and ad impressions (need 2007 Bullseye campaign data) Generate models for 120-day and 180-day windows Establish business rules using the results of testing New rules on Bullseye ad campaigns (e.g. at least 3 SKUs) Ability to revise projections at the 90-day, 60-day, 30-day windows All Bullseye ad campaigns can convert to the CPM model
Acknowledgements Sara Borthwick (manager) Entire Trax Team (Anne, Christian, Christie, Colina, Marisa, Matt, Maura, Shanna) Product Marketing (Andrew, Nina) Statisticians (Erika, Phil) Excel Master (Jared)

More Related Content

Bullseyeupdated2

  • 1. Forecasting Page Views & Ad Impressions for Bullseye Ad Campaigns David Feng Statistical Analyst Intern GEL, Trax
  • 2. What is Bullseye? Cross-game advertising A client¨s ad campaign runs exclusively on a selected game space for a set amount of time. Example I want to advertise for a new football game I created. I feel that Madden players would be interested in my game. I buy a Bullseye campaign on Madden NFL 09, since I am targetting Madden players.
  • 3. Existing Bullseye Procedures Sales team has two options Propose a predicted number of ad impressions to the client (but how much?) Charge a flat rate on the Bullseye campaign (Halo 3 = Balls of Fury) Problems Under-delivery: must compensate client in some other way C make goods Over-delivery: lost opportunity for revenue Flat-rate pricing: lost opportunity for revenue on AAA games
  • 4. Bullseye Q1¨07 Q2¨07 Q3¨07 Q4¨07 Q1¨08 Q2¨08 eCPM (censored) % of GS Revenue 9% 5% 4% 4% 3% 2%
  • 5. The Bullseye Predictive Model Objective: To provide a more objective means for predicting the number of advertising impressions in a game space. 4 phases Data-collection and processing Predict number of page views for a game space 30 days, 60 days and 90 days in advance Find the relationship between page views and advertising impressions Test validity of models and develop business rules
  • 6. The Bullseye Predictive Model Objective: To provide a more objective means for predicting the number of advertising impressions in a game space. 4 phases Data-collection and processing Predict number of page views for a game space 30 days, 60 days and 90 days in advance Find the relationship between page views and advertising impressions Test validity of models and develop business rules
  • 7. I. Data Collection Gathered data on all games released from 1/1/06 to 5/31/08 using Trax Data pulled in Mon-Sun increments 3782 games, ~2700-2800 after removing irrelevant games Computed lifecycle data for all games on the weekly level
  • 8. II: Predicting Page Views Predict page views because it should be the strongest determinant of ad impressions Determinants From Trax Users Page Views Searches Videos Served Total Users Tracking New Users Tracking Price Checks Forum Activity Pre-existing Awareness IP Type (Original, Sequel, Licensed) Milestones (News, Previews, Videos) Quality of Game Average Review Score (as a stand-in for preview score) Gamespot Traffic Quarter game is released
  • 10. Constructing the Forecast Interval Two sources of uncertainty Standard Error of Regression (SER) Coefficient Uncertainty SER Future is uncertain (see figure) Reduce through stratification (e.g. separate models for X360 games, casual games, Q4, high PV-growth) Coefficient Uncertainty Uncertain coefficients, so uncertain dependent variable Ignored Sample size not large enough Software limitation
  • 11. Solution Sell Bullseye ad campaigns on at least 3 SKUs to reduce risk of underdelivery Just need to reduce the SER to improve models¨ goodness-of-fit
  • 12. Summary of Results C 30 Days Platform Week0 Week1 Week2 Week-1 Month1 X360 PS3 Wii PC DS PSP
  • 13. Summary of Results C 60 Days Platform Week0 Week1 Week2 Week-1 Month1 X360 PS3 Wii PC DS PSP
  • 14. Summary of Results C 90 Days Platform Week0 Week1 Week2 Week-1 Month1 X360 PS3 Wii PC DS PSP
  • 15. Testing Validity of Models Use games released after 5/31/08 Test Interface & Final Interface Interface will eventually be automated into a new tool, so that the sales rep only needs to put in the game ID, and all data will be pulled from Trax A new Bullseye tool and/or an internal version of Trax could be created to ease testing and usage of the models
  • 16. Next Steps Test models Finalize relationship between page views and ad impressions (need 2007 Bullseye campaign data) Generate models for 120-day and 180-day windows Establish business rules using the results of testing New rules on Bullseye ad campaigns (e.g. at least 3 SKUs) Ability to revise projections at the 90-day, 60-day, 30-day windows All Bullseye ad campaigns can convert to the CPM model
  • 17. Acknowledgements Sara Borthwick (manager) Entire Trax Team (Anne, Christian, Christie, Colina, Marisa, Matt, Maura, Shanna) Product Marketing (Andrew, Nina) Statisticians (Erika, Phil) Excel Master (Jared)