Inferring Clickthrough Rates on Ads from Click Behavior on Search Results

Click logs provide valuable information that can be used to infer several parameters related to the relevance of search results and ads to queries. However often there are much fewer clicks on ads as compared to search results. Thus while the click logs can easily be used to study parameters related to search results the sparseness of the number of clicks for ads renders it infeasible to infer parameters related to ads. We show that the click behavior on ads is correlated with the click behavior on search results. The first correlation we show is that the drop in the CTR values as we move down the search results is correlated to the drop in CTR as we move down the ads. Second, we study the effect of the number of mainline ads on the CTR of the top ad. Finally, as an application of such correlations, we show how one can use the click data on search results to infer approximately the optimal number of ads for each query to maximize revenue from the top ad on the page.