Predicting Clicks: Estimating the Click-Through Rate for New Ads
Matthew Richardson (Microsoft Research)
Ewa Dominowska (Microsoft)
Robert Ragno (Microsoft Research)
Search engine advertising has become a significant aspect of the Web browsing experience. The order in which a search engine displays ads greatly affects the probability that a user will see and click on each ad. Consequently, the ranking has a strong impact on the revenue the search engine receives from the ads. Further, showing the user an ad that they prefer to click on also improves user satisfaction. For these reasons, it is crucially important to be able to estimate the click-through rate of ads in the system. For ads that have been repeatedly displayed, this is empirically meas-urable, but when ads initially appear, other means must be used. We show that we can use features of ads, keywords, and advertis-ers to learn a model that accurately predicts the click-though rate for an ad. We also show that using our model improves the con-vergence and performance of an advertising system. As a result, our model would improve both revenues and user satisfaction.