Optimizing Ad Delivery Through Traffic Shaping Techniques

This content explores the concept of traffic shaping to enhance ad delivery efficiency. It discusses strategies for selecting article summaries and displaying ads with the highest expected click-through rates while minimizing underdelivery risks. The goal is to combine these strategies to reduce under-delivery without a significant drop in CTR, aiming for real-time application. Various images and formulations illustrate the optimization problem, real-time solutions, and empirical results derived from the process.

• Ad Delivery
• Traffic Shaping
• Optimization
• Underdelivery
• Real-time

teey180 Follow

Uploaded on Oct 02, 2024 | 0 Views

Download Presentation

Please find below an Image/Link to download the presentation.

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.

Presentation Transcript

1. Traffic Shaping to Optimize Ad Delivery Deepayan Chakrabarti Erik Vee 1

2. Traffic Shaping Which article summary should be picked? Which ad should be displayed? Ans: The one with highest expected CTR Ans: The ad that minimizes underdelivery Article pool 2

3. 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 3

4. Traffic Shaping Which article summary should be picked? Which ad should be displayed? Ans: The one with highest expected CTR Ans: The ad that minimizes underdelivery Goal: Combine the two 4

5. Traffic Shaping Goal: Bias the article summary selection to reduce under-delivery but insignificant drop in CTR AND do this in real-time

6. Outline Formulation as an optimization problem Real-time solution Empirical results 6

7. Formulation j Demand dj i Supply sk k k:(user) j:(ads) i:(user, article) :(user, article, position) Fully Qualified Impression Goal: Infer traffic shaping fractions wki

8. Formulation A Full traffic shaping graph: All forecasted user traffic X all available articles arriving at the homepage, or directly on article page B Goal: Infer wki But forced to infer j as well C Full Traffic Shaping Graph

9. Outline Formulation as an optimization problem Real-time solution Empirical results 9

10. Formulation Reformulation: {wki, j} z j Convex program can be solved optimally 10

11. 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 11

12. Real-time solution Cache these Reconstruct using these All constraints can be expressed as constraints on 12

13. Results Data: Historical traffic logs from April, 2011 25K user nodes Total supply weight > 50B impressions 100K ads 13

14. Lift in impressions Nearly threefold improvement via traffic shaping Lift in impressions delivered to underperforming ads Fraction of traffic that is not shaped 14

15. Average CTR Average CTR (as percentage CTR drop < 10% of maximum CTR) Fraction of traffic that is not shaped 15

16. Summary 3x underdelivery reduction with <10% CTR drop 2.6x reduction with 4% CTR drop Runtime application needs only a small cache 17