Utilizing User Email Actions to Improve Ad-Close Prediction

What is it about?

Online advertising systems often provide means for users to close ads. Although closing ads requires additional user engagement and usually indicates a poor user experience, ad closes are not as scarce as one might expect. Recently it was shown that penalizing ads with a high closing likelihood during auctions may substantially reduce the number of ad closes while maintaining a small predefined revenue loss. In this work, we focus on email since this is the property in which most ad closes occur. Using data collected from a major email provider, we present interesting insights about the interplay between ad closes in email and email-related user actions. In particular, we explore the merits of integrating information derived from user actions in email for ad-close prediction. Thorough performance evaluation reveals that incorporating such signals significantly improves ad-close prediction quality over previously reported results.

Featured Image

Why is it important?

By penalizing poor ads, or ads that are likely to be closed, the system encourages the advertisers to improve the quality of their ads. At the same time, by preventing irrelevant or unsuitable ads to be displayed to the user, the user experience is improved. Improving the ability to identify such ads in a commercial system, is highly beneficial for all parties.

Perspectives