Abstract
A major trend in mobile advertising is the emergence of real time bidding (RTB) based marketplaces on the supply side and the corresponding programmatic impression buying on the demand side. In order to acquire the most relevant audience impression at the lowest cost, a demand side player has to accurately estimate the win rate and winning price in the auction, and incorporate that knowledge in its bid. In this paper, we describe our battle-proven techniques of predicting win rate and winning price in RTB, and the corresponding bidding strategies built on top of those predictions. We also reveal the close relationship between the win rate and winning price estimation, and demonstrate how to solve the two problems together. All of our estimation methods are developed with distributed framework and have been applied to billion order numbers of data in real business operation.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Apache software foundation, Scalable machine learning and data mining (2013), http://mahout.apache.org
Langford, J.: Wowpal wabbit (2013), https://github.com/JohnLangford/vowpal_wabbit/wiki
Schapire, R., Stone, P., McAllester, D., Littman, M., Csirik, J.: Modeling auction price uncertainty using boosting-based conditional density estimation. In: ICML 2002 (2002)
Wellman, M., Greenwald, A., Stone, P., Wurman, P.: The 2001 trading agent competition. Electronic Markets 13, 4–12 (2003)
Wellman, M., Reeves, D., Lochner, K., Vorobeychik, Y.: Price prediction in a trading agent competition. Journal of Artificial Intelligence Research 21, 19–36 (2004)
Putchala, R., Morris, V., Kazhanchi, R., Raman, L., Shekhar, S.: kavayaH: A trading agent developed for TAC-02. Tech. Rep., Oracle India (2002)
He, M., Jennings, N.: SouthamptonTAC: An adaptive autonomous trading agent. ACM Transactions on Internet Technology 3, 218–235 (2003)
Greenwald, A., Lee, S., Naroditskiy, V.: RoxyBot-06: Stochastic prediction and optimization in TAC travel. Journal of Artificial Intelligence Research 36, 513–546 (2009)
Hosmer, D., Lemeshow, S.: Applied logistic Regression, 2nd edn. John Wiley and Sons (2000)
Richardson, M., Dominowska, E., Ragno, R.: Predicting clicks: estimating the click-through rate for new ads. In: Proceedings of WWW 2007, pp. 521–530 (2007)
Interian, Y., Dorai-Raj, S., Naverniouk, I., Opalinski, P., Kaustuv, Zigmond, D.: Ad quality on tv: Predicting television audience retention. In: ADKDD (2009)
Becker, H.: Modeling contextual factors of click rates. In: Proceedings of AAAI Conference on Artificial Intelligence, pp. 1310–1315 (2007)
Sculley, D., Malkin, R., Basu, S., Bayardo, R.: Predicting bounce rates in sponsored search advertisements. In: SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), pp. 1325–1334 (2009)
Edelman, B., Ostrovsky, M., Schwarz, M., Fudenberg, T., Kaplow, L., Lee, R., Milgrom, P., Niederle, M., Pakes, A.: Internet advertising and the generalized second price auction: selling billions of dollars worth of keywords. American Economic Review 97 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Li, X., Guan, D. (2014). Programmatic Buying Bidding Strategies with Win Rate and Winning Price Estimation in Real Time Mobile Advertising. In: Tseng, V.S., Ho, T.B., Zhou, ZH., Chen, A.L.P., Kao, HY. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2014. Lecture Notes in Computer Science(), vol 8443. Springer, Cham. https://doi.org/10.1007/978-3-319-06608-0_37
Download citation
DOI: https://doi.org/10.1007/978-3-319-06608-0_37
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-06607-3
Online ISBN: 978-3-319-06608-0
eBook Packages: Computer ScienceComputer Science (R0)