Ad Allocation for Browse Sessions

A user’s session of information need often goes well beyond his search query and first click on the search result page and therefore is characterized by both search and browse activities on the web. In such settings, the effectiveness of an ad (measured as CtoC ratio, as well as #(conversions) per unit payment) could change based on what pages the user visits and the ads he encounters earlier in the session. We assume that an advertiser’s welfare is solely derived from conversions. Our first contribution is to show that the effectiveness of an ad depends upon the past events in the session, namely past exposure to self as well as to competitors. To this end, we analyze logs of user activity over a period of one month from Microsoft AdCenter Delivery Engine. We then propose a new bidding language that allows the advertiser to specify his valuation of a user’s click as a function of these externalities, and study the improvement in prediction of conversion events with the new bidding language. We also study theoretical aspects of the allocation problem under new bidding language and conduct an extensive empirical analysis to measure effectiveness of our proposed allocation schemes.