Prediction and Welfare in Ad Auctions
We study how standard auction objectives in sponsored search markets are affected by refinement in the prediction of ad relevance (click-through rates). As the prediction algorithm takes more features into account, its predictions become more refined; a natural question is whether this is desirable from the perspective of auction objectives. Our focus is on mechanisms that optimize for a convex combination of efficiency and revenue, and our starting point is the observation that the objective of such a mechanism can only improve with refined prediction, making refinement in the best interest of the search engine. We demonstrate that the impact of refinement on market efficiency is not always positive; nevertheless we are able to identify natural – and to some extent necessary – conditions under which refinement is guaranteed to also improve efficiency. Our main technical contribution is in explaining how refinement changes the ranking of advertisers by value (efficiency-ranking), moving it either towards or away from their ranking by virtual value (revenue-ranking). These results are closely related to the literature on signaling in auctions.
KeywordsPareto Frontier Prediction Scheme Optimal Mechanism Partial Ranking Truthful Mechanism
Unable to display preview. Download preview PDF.
- 1.Aggarwal, G., Goel, A., Motwani, R.: Truthful auctions for pricing search keywords. In: Proc. 8th EC (2006)Google Scholar
- 5.Emek, Y., Feldman, M., Gamzu, I., Leme, R.P., Tennenholtz, M.: Signaling schemes for revenue maximization. In: EC, pp. 514–531 (2012)Google Scholar
- 6.Ewerhart, C.: Optimal design and ρ-concavity, working Paper (2009)Google Scholar
- 9.Graepel, T., Candela, J.Q., Borchert, T., Herbrich, R.: Web-scale bayesian click-through rate prediction for sponsored search advertising in Microsoft’s Bing search engine. In: 27th International Conference on Machine Learning (2010)Google Scholar
- 11.Lahaie, S., Pennock, D.M.: Revenue analysis of a family of ranking rules for keyword auctions. In: EC, pp. 50–56 (2007)Google Scholar
- 12.Lahaie, S., Pennock, D.M., Saberi, A., Vohra, R.V.: Sponsored search auctions. In: Nisan, N., Roughgarden, T., Tardos, É., Vazirani, V. (eds.) Algorithmic Game Theory, ch. 28, pp. 699–716. Cambridge University Press (2007)Google Scholar
- 13.Likhodedov, A., Sandholm, T.: Auction mechanism for optimally trading off revenue and efficiency. In: EC, pp. 212–213 (2003)Google Scholar
- 14.McAfee, R., McMillan, J.: Auctions and bidding. Journal of Economic Literature 25(2), 699–738 (1987)Google Scholar
- 15.Mehta, A., Saberi, A., Vazirani, U., Vazirani, V.: Adwords and generalized on-line matching. In: Proc. 46th IEEE Symp. on Foundations of Computer Science, FOCS (2002)Google Scholar
- 17.Miltersen, P.B., Sheffet, O.: Send mixed signals: earn more, work less. In: EC, pp. 234–247 (2012)Google Scholar
- 20.Sundararajan, M., Talgam-Cohen, I.: Refine predictions ad infinitum? (2013), http://arxiv.org/abs/1302.6700