Ranking of New Sponsored Online Ads Using Semantically Related Historical Ads

Online advertising in search engines is a wide and growing market. In this market, revenue of search engines depends on the number of user clicks received on displayed ads. Thus, in order to increase the revenue, search engines try to select top ads and rank them based on the expected number of clicks they will receive. For ads that were in the system for a period of time, the expected number of clicks could be estimated based on historical data. For new ads, or those ads without enough historical data, search engines need to predict the potential of these ads in attracting user clicks. We purpose a method to estimate the potential of new ads in attracting user’s clicks. We use semantic and feature based similarity algorithms to predict the click through rate of new ads using historical similar ads. Our trace-based evaluations show that the proposed method outperforms other approaches in the literature in terms of the accuracy of prediction. In addition, the proposed method is less computationally expensive than previous methods and it can run in real time.