T2-based MRI Delta-Radiomics Improve Response Prediction ...
Response Prediction in Performance based Display Advertisingcomad/2010/pdf/Industry...
Transcript of Response Prediction in Performance based Display Advertisingcomad/2010/pdf/Industry...
![Page 1: Response Prediction in Performance based Display Advertisingcomad/2010/pdf/Industry Sessions/Response... · Response Prediction in Performance based Display Advertising-1-Krishna](https://reader034.fdocuments.us/reader034/viewer/2022042107/5e8666a298c9b73f5741fcc7/html5/thumbnails/1.jpg)
Response Prediction in Performance based Display Advertising
- 1 -
Advertising
Krishna Prasad Chitrapura
Yahoo! Labs, Bangalore
![Page 2: Response Prediction in Performance based Display Advertisingcomad/2010/pdf/Industry Sessions/Response... · Response Prediction in Performance based Display Advertising-1-Krishna](https://reader034.fdocuments.us/reader034/viewer/2022042107/5e8666a298c9b73f5741fcc7/html5/thumbnails/2.jpg)
Overview
• History of display advertisement
– From traditional print media to day.
• Why response prediction?
• Why is response prediction a hard
- 2 -
• Why is response prediction a hard
problem?
– What worked and what didn’t
• Summary and pointers
![Page 3: Response Prediction in Performance based Display Advertisingcomad/2010/pdf/Industry Sessions/Response... · Response Prediction in Performance based Display Advertising-1-Krishna](https://reader034.fdocuments.us/reader034/viewer/2022042107/5e8666a298c9b73f5741fcc7/html5/thumbnails/3.jpg)
History (Traditional media)
• Online display ad market mimicked the traditional media in early 90s. Publisher inventory was sold in
- 3 -
inventory was sold in bulk to advertisers
• Each Website was a publisher and involved lots of manual sales force.
![Page 4: Response Prediction in Performance based Display Advertisingcomad/2010/pdf/Industry Sessions/Response... · Response Prediction in Performance based Display Advertising-1-Krishna](https://reader034.fdocuments.us/reader034/viewer/2022042107/5e8666a298c9b73f5741fcc7/html5/thumbnails/4.jpg)
History (Network centric)
• This morphed into simple networks where aggregation of supply (eye balls) and demand (ads inventory) increased value. (Late 90s and early 2000).
- 4 -
90s and early 2000).
• Each large publisher had a network – Yahoo! Aol, MSN, etc.
• Different pricing models evolved such as pay per click (CPC), pay per view (CPM), pay per user action (CPA).
![Page 5: Response Prediction in Performance based Display Advertisingcomad/2010/pdf/Industry Sessions/Response... · Response Prediction in Performance based Display Advertising-1-Krishna](https://reader034.fdocuments.us/reader034/viewer/2022042107/5e8666a298c9b73f5741fcc7/html5/thumbnails/5.jpg)
History (Ad Exchange)
• Networks of networks resulted in better matching of
supply to demand and had built-in incentives to share
data about the inventory.
CPA $4.00 x25% chance =>Bids $0.50
Bids $0.75 via Network…
Bids $0.60
Need to compute the probability of click / conversion to help pick the best ad
- 5 -
Has ad impression it
can’t sell for premium --
AUCTIONS … which becomes $0.45 bid
AdSense
CPC $1.40 (x50%) => Bids $0.70—WINS!
pick the best ad
Ad Serving Stack
Ad Tag Parsing
Targeting
Budget Checks
Ad Selection & Display
Reporting
Response Prediction
![Page 6: Response Prediction in Performance based Display Advertisingcomad/2010/pdf/Industry Sessions/Response... · Response Prediction in Performance based Display Advertising-1-Krishna](https://reader034.fdocuments.us/reader034/viewer/2022042107/5e8666a298c9b73f5741fcc7/html5/thumbnails/6.jpg)
History (Ad Exchange)
CPA $4.00 x25% chance =>Bids $0.50
Bids $0.75 via Network…
Network X
Bids $0.60
Need to compute the probability of click / conversion to help pick the best ad
Ad Serving Stack
Ad Tag Parsing
Targeting
- 6 -
Has ad impression it
can’t sell for premium --
AUCTIONS … which becomes $0.45 bid
CPC $1.40 (x50%) => Bids $0.70—WINS!
Networks of networks resulted in better matching of supply to demand and had built-in
incentives to share data about the inventory.
Targeting
Budget Checks
Ad Selection & Display
Reporting
Response Prediction
![Page 8: Response Prediction in Performance based Display Advertisingcomad/2010/pdf/Industry Sessions/Response... · Response Prediction in Performance based Display Advertising-1-Krishna](https://reader034.fdocuments.us/reader034/viewer/2022042107/5e8666a298c9b73f5741fcc7/html5/thumbnails/8.jpg)
Problem(s):
• Extremely large dimensional space O(B pages × 100 M user × few M ads)
• Extreme sparsity – Click through rate and conversion rates are small.
• Data quality (frauds, missing value,…) and
- 8 -
• Data quality (frauds, missing value,…) and duplicity results in biased estimates.
• Is it a regression problem?
– Not directly thanks to small rates.
• Is it a classification problem (c/ĉ)?
– Not directly thanks to skew in class distribution
![Page 9: Response Prediction in Performance based Display Advertisingcomad/2010/pdf/Industry Sessions/Response... · Response Prediction in Performance based Display Advertising-1-Krishna](https://reader034.fdocuments.us/reader034/viewer/2022042107/5e8666a298c9b73f5741fcc7/html5/thumbnails/9.jpg)
What was tried and tested?
• Linear regression/classification.
– CTR estimates were not in [0,1].
– Bounding did not help
• Logistic regression.
– Sigmoid function does not separate the data well.
- 9 -
– Moving to log scale helped although marginally.
• Latent Space models.
– Regularized SVD with modifications to handle confidence helped.
• Smoothing the estimates on a hierarchy helped the most.
![Page 10: Response Prediction in Performance based Display Advertisingcomad/2010/pdf/Industry Sessions/Response... · Response Prediction in Performance based Display Advertising-1-Krishna](https://reader034.fdocuments.us/reader034/viewer/2022042107/5e8666a298c9b73f5741fcc7/html5/thumbnails/10.jpg)
Response Prediction as Matrix completion
• Consider a m ✕ n matrix of X of users demographics by advertisements.
• Each cell Xij is the empirical click probability based on historical data. Xij=Cij/Vij for click and view matrices C,V.
• Problem 1: Smoothen X for the observed
- 10 -
• Problem 1: Smoothen Xij for the observed cells.
• Especially for cells very few views.
• Problem 2: Estimate Xij for the unobserved cells.
– If an ad has never been shown or has no clicks.
![Page 11: Response Prediction in Performance based Display Advertisingcomad/2010/pdf/Industry Sessions/Response... · Response Prediction in Performance based Display Advertising-1-Krishna](https://reader034.fdocuments.us/reader034/viewer/2022042107/5e8666a298c9b73f5741fcc7/html5/thumbnails/11.jpg)
Matrix factorization
• Learn k latent features for the rows and columns via the non-convex optimization. (aka reguralized SVD)
• In addition, Fix U, optimize V. We need a
minU ,V
(X ij −Ui
TV j )
2+
λU
2U
F
2+
λV
2V
F
2
(i, j )∈Ο
∑
- 11 -
• In addition, Fix U, optimize V. We need a ridge function to constrain the regression
• Throw in confidence,
• Trust MLE for high view cells.
minU ,V
− Cij logσ (Ui
TV j ) + (Vij − Cij )log(1−σ(
( i, j )∈Ο
∑ Ui
TV j )) +
λU
2U
F
2+
λV
2V
F
2
![Page 12: Response Prediction in Performance based Display Advertisingcomad/2010/pdf/Industry Sessions/Response... · Response Prediction in Performance based Display Advertising-1-Krishna](https://reader034.fdocuments.us/reader034/viewer/2022042107/5e8666a298c9b73f5741fcc7/html5/thumbnails/12.jpg)
How does hierarchies help?
• The data can be arranged in multiple hierarchies
– Ad hierarchy: Advertiser – campaign – ad_creative
– Publisher : Publisher – site – sub-site-page
– User : demographic hierarchy such as geo
• MLE at coarser levels of the tree have more confidence.
- 12 -
confidence.
– Smoothing/adding constraints based on coarser level bins reduces variance and bias.
• Couple of ideas:
– Smoothen finer grained cells based on estimates in coarser bin.
– Correct bias in finer grained bins based on aggregates in coarser bin.
![Page 13: Response Prediction in Performance based Display Advertisingcomad/2010/pdf/Industry Sessions/Response... · Response Prediction in Performance based Display Advertising-1-Krishna](https://reader034.fdocuments.us/reader034/viewer/2022042107/5e8666a298c9b73f5741fcc7/html5/thumbnails/13.jpg)
More details
• Deepak Agarwal et al. “Estimating Rates of Rare Events with Multiple Hierarchies through Scalable Log-linear Models”, KDD 2010.
• Adiya Menon et al. “Collaborative filtering
- 13 -
• Adiya Menon et al. “Collaborative filtering using hierarchies for response prediction” under review
• Yahoo! Shares data to academic researchers under Webscope programme. See: http://webscope.sandbox.yahoo.com/