Abstract
In the real-time bidding (RTB) display advertising ecosystem, when receiving a bid request, Demand-side platform (DSP) needs to predict user response on each ad impression and determines whether to bid and calculates the bid price according to its prediction. When given a fixed advertising budget, in order to maximize the return on investment (ROI), DSP aims to buy in more conversions and then more clicks than non-clicks. In this paper, we consider response prediction problem as a ranking problem for impression chances and propose a triplet-wise comparison based learning optimization which derived from Bayesian personalized ranking (BPR) based on pairwise learning to learn model parameters. Pairwise learning can only employ one type of historical click and conversion information through optimizing the correct order of random pair of a positive and a negative example for binary classification. While triplet-wise learning combines these two kinds of historical response information into the same model through taking into consideration the correct order of the pair of conversion and click-only as well as the pair of click-only and non-click. Since our method accomplishes the click and conversion prediction tasks in the same predicting procedure, our algorithm is good at ranking click impressions higher than non-click ones and conversion impressions higher than click-only ones. In this way, under a fixed budget, biding algorithm would preferentially buy in more conversions than others and then more clicks than non-clicks. Our experiments demonstrate that the improved method not only outperforms both pairwise and MSE schemes on three classes ranking in terms of multi-AUC, NDCG etc., but also, outperforms others on binary classification for click and non-click on the targeted real-world bidding log data owing to the introduction of historical conversion information.
Similar content being viewed by others
References
Chapelle O, Manavoglu E, Rosales R (2014) Simple and scalable response prediction for display advertising. ACM Trans Intell Syst Technol 5(4):61. doi:10.1145/2532128
Chen T, Zheng Z, Lu Q, Zhang W, Yu Y (2011) Feature-based matrix factorization. Proceedings of the 2nd Challenge on Context-Aware Movie Recommendation. ACM. http://svdfeature.apexlab.org/wiki/images/7/76/APEX-TR-2011-07-11.pdf. Accessed 26 October 2015
Cortes, C, Mehryar M (2004) AUC optimization vs. error rate minimization. Proceedings of advances in neural information processing systems, vol 16. pp 313–320
Fawcett T (2004) ROC graphs: notes and practical considerations for researchers. Machine learning 31. Kluwer Academic Publishers, Dordrecht, the Netherlands, pp 1–38
Ferri C, Flach P, Hernández-Orallo J (2002) Learning decision trees using the area under the ROC curve. ICML 2:139–146
Freund Y, Iyer R, Schapire RE, Singer Y (2003) An efficient boosting algorithm for combining preferences. J Mac Learn Res 4:933–969
Hand DJ, Till RJ (2001) A simple generalization of the area under the ROC curve to multiple class classification problems’. Mach Learn 45(2):171–186
Herschtal A, R Bhavani (2004) Optimising area under the ROC curve using gradient descent. doi:10.1145/1015330.1015366
Kalervo Järvelin and Jaana Kekäläinen (2000), IR evaluation methods for retrieving highly relevant documents International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, pp. 41–48
Lee K-c, Burkay O, Ali D, Li W (2012). Estimating conversion rate in display advertising from past performance data. Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 768–776
Li C, Lu Y, Mei Q, et al. (2015) Click-through prediction for advertising in twitter timeline. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM. pp. 1959–1968
Liao H, Lingxiao P, Zhenchuan L, Xuehua S (2014) iPinYou Global RTB Bidding Algorithm Competition Dataset. In Proceedings of 20th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, ACM. pp. 1–6
Liu TY, Xu J, Qin T et al (2007) LETOR: benchmark Dataset for Research on Learning to Rank for Information Retrieval[J]. Proc SIGIR Workshop Learn Rank Info Retrieval 41(2):76–79
Lü Luan, Medo M, Yeung CH, Zhang Y-C, Zhang Z-K, Zhou T (2012) Recommender systems. Phys Rep 519:1–49
Mozer, MC (2003) Optimizing classifier performance via an approximation to the Wilcoxon-Mann–Whitney statistic. Proceedings of the 19th International Conference on Machine Learning. pp. 848–855
Menon A, Krishna C, Krishna P, Garg S, Agarwal D, Kota N (2011) Response prediction using collaborative filtering with hierarchies and side-information. Processing of the 17th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. pp. 141–149
Metwally A, Agrawal D, El Abbadi A. (2007) Detectives: detecting coalition hit inflation attacks in advertising networks streams Proceedings of the 16th international conference on World Wide Web. ACM. pp. 241–250
Platt JC (2000) Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods. Advances in Large Margin Classifiers 10:61–74
Rendle S, Schmidt-Thieme L (2010) Pairwise interaction tensor factorization for personalized tag recommendation. Wsdm 10 Third Acm International Conference on Web Search & Data Mining. pp. 81–90
Rendle S, Christoph F, Zeno G, Lars S-T (2009) BPR: Bayesian personalized ranking from implicit feedback. Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence, pp 452–461
Sculley D (2010) Combined regression and ranking Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM. pp. 979–988
Shan L, Lin L, Shao D, Wang X (2014) CTR Prediction for DSP with Improved Cube Factorization Model from Historical Bidding Log. Processing of the 21st International Conference on Neural Information Processing. pp. 17–24
Shan Lili, Lin Lei, Sun Chengjie et al (2016) Predicting ad click-through rates via feature-based fully coupled interaction tensor factorization[J]. Electron Commer Res Appl 16:30–42
Shen S, Hu B, Chen W, Yang Q (2012) Personalized click model through collaborative filtering. Proceedings of the fifth ACM international conference on Web search and data mining. pp. 323–332. doi:10.1145/2124295.2124336
Tagami Y, Ono S, Yamamoto K et al. (2013) CTR prediction for contextual advertising: Learning-to-rank approach. Proceedings of the Seventh International Workshop on Data Mining for Online Advertising. ACM: 4
Wang XZ (2015) Uncertainty in Learning from Big Data-Editorial. J Intell Fuzzy Syst 28(5):2329–2330
Wu K-W, Ferng C-S, Ho C-H, Liang A-C, Huang C-H, Shen W.-Y et al (2012) A two-stage ensemble of diverse models for advertisement ranking. The 18th ACM KDDCUP.
Wang XZ, Ashfaq RAR, Fu AM (2015) Fuzziness based sample categorization for classifier performance improvement. J Intell Fuzzy Syst 29(3):1185–1196
Yan L, Li WJ, Xue GR, Han D (2014) Coupled Group Lasso for Web-Scale CTR Prediction in Display Advertising. Proceedings of the 31st International Conference on Machine Learning:, pp. 802–810
Zhang W, Yuan S, Wang J, Shen X (2014) Real-time bidding benchmarking with ipinyou dataset. arXiv preprint arXiv:1407.7073
Acknowledgments
This work is supported by the National Natural Science Foundation of China (No. 61300114 and No. 61572151) and China Postdoctoral Science special Foundation (No. 2014T70340).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Shan, L., Lin, L., Sun, C. et al. Optimizing ranking for response prediction via triplet-wise learning from historical feedback. Int. J. Mach. Learn. & Cyber. 8, 1777–1793 (2017). https://doi.org/10.1007/s13042-016-0558-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-016-0558-3