1 / 5

Estimating Click-Through Rate for New Ads: Methods, Features, and Challenges

Click-Through Rate (CTR) is essential for ad ranking, but calculating CTR for new ads poses challenges compared to established ads. This work explores alternative methods to predict CTR for new ads, identifying 81 features across categories like Appearance, Attention Capture, Reputation, Landing Page Quality, and Relevance. While aiming for a more accurate CTR estimation through weighted combinations of these features, it draws criticism for lacking standard datasets, computing CTR independently of queries, and failing to provide actionable insights for advertisers. The study also touches on the complexities of comparing ad features.

Download Presentation

Estimating Click-Through Rate for New Ads: Methods, Features, and Challenges

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Estimating CTR for New Ads CTR is a component in determining the ranking of ads for a given query. For old ads CTR is easy to compute. For new ads some other method is to be used. Previous work focused on same bid-terms. Problem: CTR of the best ad can be ten times that of the average ad.

  2. Solution • Identify features for an ad from the following categories: -Appearance, Attention Capture, Reputation, Landing Page Quality, Relevance. • Total of 81 features used to find the CTR for a new ad. • Weighted Combination of each of the featureused to predict CTR for new ad.

  3. Criticism • No standard data-set • Computing the CTR independent of the query. • Does not allow advertiser’s recommendations for improving their CTR value • Have not highlighted on the fraudulent issues relating to web

  4. Relation • Apples+Oranges of features • Pageranking-CTR

More Related