170 likes | 321 Views
Traffic Shaping to Optimize Ad Delivery. Deepayan Chakrabarti Erik Vee. Traffic Shaping. Which article summary should be picked? Ans : The one with highest expected CTR. Which ad should be displayed? Ans : The ad that minimizes underdelivery. Article pool. Underdelivery.
E N D
Traffic Shaping to Optimize Ad Delivery DeepayanChakrabarti Erik Vee
Traffic Shaping Which article summary should be picked? Ans:The one with highest expected CTR Which ad should be displayed? Ans:The ad that minimizes underdelivery Article pool
Underdelivery • Advertisers are guaranteed some impressions (say, 1M) over some time (say, 2 months) • only to users matching their specs • only when they visit certain types of pages • only on certain positions on the page • An underdelivering ad is one that is likely to miss its guarantee
Traffic Shaping Which article summary should be picked? Ans:The one with highest expected CTR Which ad should be displayed? Ans:The ad that minimizes underdelivery Goal: Combine the two
Traffic Shaping • Goal: Bias the article summary selection to • reduce under-delivery • but insignificant drop in CTR • AND do this in real-time
Outline • Formulation as an optimization problem • Real-time solution • Empirical results
Formulation Ad delivery fraction φℓj ℓ j Demand dj Traffic shaping fraction wki i Supply sk CTRcki k k:(user) j:(ads) i:(user, article) ℓ:(user, article, position)“Fully Qualified Impression” Goal: Infer traffic shaping fractions wki
Ad delivery fraction φℓj Formulation Traffic shaping fraction wki A CTRcki • Full traffic shaping graph: • All forecasted user traffic X all available articles • arriving at the homepage, • or directly on article page • Goal: Infer wki • But forced to infer φℓjas well B C Full Traffic Shaping Graph
Outline • Formulation as an optimization problem • Real-time solution • Empirical results
Formulation • Reformulation: {wki, φℓj}→ zℓj • Convex program can be solved optimally
Formulation • But we have another problem • At runtime, we must shape every incoming user without looking at the entire graph • Solution: • Periodically solve the convex problem offline • Store a cache derived from this solution • Reconstruct the optimal solution for each user at runtime, using only the cache
Real-time solution Cache these Reconstruct using these All constraints can be expressed as constraints on σℓ
Results • Data: • Historical traffic logs from April, 2011 • 25K user nodes • Total supply weight > 50B impressions • 100K ads
Lift in impressions Nearly threefold improvement via traffic shaping Lift in impressions delivered to underperforming ads Fraction of traffic that is not shaped
Average CTR CTR drop < 10% Average CTR (as percentage of maximum CTR) Fraction of traffic that is not shaped
Summary • 3x underdelivery reduction with <10% CTR drop • 2.6x reduction with 4% CTR drop • Runtime application needs only a small cache