Sponsored Search Auction Design via Machine Learning

In this work we use techniques from the study of samplecomplexity in machine learning to reduce revenue maximizing auction problems to standard algorithmic questions. These results are particularly relevant to designing good pricing mechanisms for sponsored search. In particular we apply our results to two problems: profit maximizing combinatorial auctions, and auctions for pricing semantically related goods. Auctions for sponsored search can be viewed as combinatorial auctions in that bidders have combinatorial (in the search terms and the location of the ad on the search results page) preferences for having ads placed. Furthermore since the space of all searches is much larger than the set of advertisers, it is useful to use the semantic relationship of search terms within pricing algorithms. Our main results show how to take algorithms that solve these pricing problems and convert them into auctions with good game-theoretic properties and provably good performance.