Keyword-level Bayesian online bid optimization for sponsored search advertising. (English) Zbl 1541.90224
Summary: Bid price optimization in online advertising is a challenging task due to its high uncertainty. In this paper, we propose a bid price optimization algorithm focused on keyword-level bidding for pay-per-click sponsored search ads, which is a realistic setting for many firms. There are three characteristics of this setting: “The setting targets the optimization of bids for each keyword in pay-per-click sponsored search advertising”, “The only information available to advertisers is the number of impressions, clicks, conversions, and advertising cost for each keyword”, and “Advertisers bid daily and set monthly budgets on a campaign basis”. Our algorithm first predicts the performance of keywords as a distribution by modeling the relationship between ad metrics through a Bayesian network and performing Bayesian inference. Then, it outputs the bid price by means of a bandit algorithm and online optimization. This approach enables online optimization that considers uncertainty from the limited information available to advertisers. We conducted simulations using real data and confirmed the effectiveness of the proposed method for both open-source data and data provided by negocia, Inc., which provides an automated Internet advertising management system.
MSC:
| 90B60 | Marketing, advertising |
Keywords:
online advertising; bid price optimization; Bayesian inference; bandit algorithm; online optimizationReferences:
| [1] | eMarketer (2022) TV Ad spending 2022 - insider intelligence trends, forecasts & statistics. https://www.insiderintelligence.com/content/tv-ad-spending-2022. Accessed 23 Apr 2023 |
| [2] | IAB (2022) Iab internet advertising revenue report full year 2021. https://www.iab.com/wp-content/uploads/2022/04/IAB_Internet_Advertising_Revenue_Report_Full_Year_2021.pdf. Accessed 23 Apr 2023 |
| [3] | Liao H, Peng L, Liu Z et al (2014) iPinYou global RTB bidding algorithm competition dataset. Proceedings of the 8th International Workshop on Data Mining for Online Advertising. pp 1-6. doi:10.1145/2648584.2648590 |
| [4] | Amazon Ads (2023) How does bidding work with amazon ads? https://advertising.amazon.com/en-us/library/videos/campaign-bidding-sponsored-products. Accessed 23 Apr 2023 |
| [5] | Google Ads (2023) About quality score. https://support.google.com/google-ads/answer/6167118. Accessed 23 April 2023 |
| [6] | LocaliQ (2022) Search advertising benchmarks for every industry [2022 data]. https://localiq.com/blog/search-advertising-benchmarks/. Accessed 23 Apr 2023 |
| [7] | Feng Z, Podimata C, Syrgkanis V (2018) Learning to bid without knowing your value. Proceedings of the 2018 ACM Conference on Economics and Computation. pp 505-522. doi:10.1145/3219166.3219208 |
| [8] | Abhishek, V.; Hosanagar, K., Optimal bidding in multi-item multislot sponsored search auctions, Oper Res, 61, 4, 855-873, 2013 · Zbl 1291.91080 · doi:10.1287/opre.2013.1187 |
| [9] | Thomaidou, S.; Liakopoulos, K.; Vazirgiannis, M., Toward an integrated framework for automated development and optimization of online advertising campaigns, Intell Data Anal, 18, 6, 1199-1227, 2014 · doi:10.3233/IDA-140691 |
| [10] | Zhang W, Zhang Y, Gao B et al (2012) Joint optimization of bid and budget allocation in sponsored search. Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp 1177-1185. doi:10.1145/2339530.2339716 |
| [11] | Li H, Lei Y, Yang Y (2019) Bidding strategies on Adgroup and keyword levels in search engine advertising: a comparison study. Proceedings of the 2019 2nd International Conference on Information Management and Management Sciences. pp 23-27. doi:10.1145/3357292.3357307 |
| [12] | Auer, P.; Cesa-Bianchi, N.; Freund, Y., The nonstochastic multiarmed bandit problem, SIAM J Comput, 32, 1, 48-77, 2002 · Zbl 1029.68087 · doi:10.1137/S0097539701398375 |
| [13] | Rusmevichientong P, Williamson DP (2006) An adaptive algorithm for selecting profitable keywords for search-based advertising services. Proceedings of the 7th ACM Conference on Electronic Commerce. pp 260-269. doi:10.1145/1134707.1134736 |
| [14] | Symitsi, E.; Markellos, RN; Mantrala, MK, Keyword portfolio optimization in paid search advertising, Eur J Oper Res, 303, 2, 767-778, 2022 · Zbl 1524.90196 · doi:10.1016/j.ejor.2022.03.006 |
| [15] | Yang, Y.; Zhang, J.; Qin, R., Budget strategy in uncertain environments of search auctions: a preliminary investigation, IEEE Trans Serv Comput, 6, 2, 168-176, 2012 · doi:10.1109/TSC.2011.60 |
| [16] | Avadhanula, V.; Colini Baldeschi, R.; Leonardi, S., Stochastic bandits for multi-platform budget optimization in online advertising, Proceedings of the Web Conference, 2021, 2805-2817, 2021 |
| [17] | Nuara, A.; Trovò, F.; Gatti, N., Online joint bid/daily budget optimization of internet advertising campaigns, Artif Intell, 305, 103663, 2022 · Zbl 07505973 · doi:10.1016/j.artint.2022.103663 |
| [18] | Badanidiyuru, A.; Kleinberg, R.; Slivkins, A., Bandits with knapsacks, J ACM, 65, 3, 1-55, 2018 · Zbl 1425.68340 · doi:10.1145/3164539 |
| [19] | Chen W, Wang Y, Yuan Y (2013) Combinatorial multi-armed bandit: general framework and applications. Proceedings of the 30th International Conference on International Conference on Machine Learning. pp 151-159. https://proceedings.mlr.press/v28/chen13a.html |
| [20] | Srinivas N, Krause A, Kakade S et al (2010) Gaussian process optimization in the bandit setting: no regret and experimental design. Proceedings of the 27th International Conference on International Conference on Machine Learning. pp 1015-1022. doi:10.5555/3104322.3104451 |
| [21] | Agarwal, A.; Hosanagar, K.; Smith, MD, Location, location, location: an analysis of profitability of position in online advertising markets, J Mark Res, 48, 6, 1057-1073, 2011 · doi:10.1509/jmr.08.0468 |
| [22] | Du, X.; Su, M.; Zhang, X., Bidding for multiple keywords in sponsored search advertising: keyword categories and match types, Inf Syst Res, 28, 4, 711-722, 2017 · doi:10.1287/isre.2017.0724 |
| [23] | Ghose, A.; Yang, S., An empirical analysis of search engine advertising: sponsored search in electronic markets, Manage Sci, 55, 10, 1605-1622, 2009 · doi:10.1287/mnsc.1090.1054 |
| [24] | Hou, L., A hierarchical Bayesian network-based approach to keyword auction, IEEE Trans Eng Manage, 62, 2, 217-225, 2015 · doi:10.1109/TEM.2015.2390772 |
| [25] | Yang, H.; Ormandi, R.; Tsao, HY, Estimating rates of rare events through a multidimensional dynamic hierarchical Bayesian framework, Appl Stoch Model Bus Ind, 32, 3, 340-353, 2016 · doi:10.1002/asmb.2150 |
| [26] | Yang, S.; Ghose, A., Analyzing the relationship between organic and sponsored search advertising: positive, negative, or zero interdependence?, Mark Sci, 29, 4, 602-623, 2010 · doi:10.1287/mksc.1090.0552 |
| [27] | Watanabe, S.; Opper, M., Asymptotic equivalence of Bayes cross validation and widely applicable information criterion in singular learning theory, J Mach Learn Res, 11, 12, 3571-3594, 2010 · Zbl 1242.62024 |
| [28] | Zhang W, Yuan S, Wang J (2014) Optimal real-time bidding for display advertising. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp 1077-1086. doi:10.1145/2623330.2623633 |
| [29] | Hoffman, MD; Blei, DM; Wang, C., Stochastic variational inference, J Mach Learn Res, 14, 1, 1303-1347, 2013 · Zbl 1317.68163 |
| [30] | Metropolis, N.; Rosenbluth, AW; Rosenbluth, MN, Equation of state calculations by fast computing machines, J Chem Phys, 21, 6, 1087-1092, 1953 · Zbl 1431.65006 · doi:10.1063/1.1699114 |
| [31] | Auer, P.; Cesa-Bianchi, N.; Fischer, P., Finite-time analysis of the multiarmed bandit problem, Mach Learn, 47, 2, 235-256, 2002 · Zbl 1012.68093 · doi:10.1023/A:1013689704352 |
| [32] | Chapelle O, Li L (2011) An empirical evaluation of Thompson sampling. Proceedings of the 24th International Conference on Neural Information Processing Systems. pp 2249-2257. https://papers.nips.cc/paper_files/paper/2011/hash/e53a0a2978c28872a4505bdb51db06dc-Abstract.html |
| [33] | Gurobi Optimization, LLC (2022) Gurobi optimizer reference manual. https://www.gurobi.com. Accessed 23 Apr 2023 |
| [34] | Phan D, Pradhan N, Jankowiak M (2019) Composable effects for flexible and accelerated probabilistic programming in numpyro. Preprint at http://arxiv.org/abs/1912.11554 |
| [35] | Fix, E.; Hodges, JL, Discriminatory analysis. nonparametric discrimination: consistency properties, International Statistical Review/Revue Internationale de Statistique, 57, 3, 238-247, 1989 · Zbl 0715.62080 |
| [36] | Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. Proceedings of the 3rd International Conference on Learning Representations. doi:10.48550/arXiv.1412.6980 |
| [37] | Kumar, R.; Carroll, C.; Hartikainen, A., Arviz a unified library for exploratory analysis of Bayesian models in python, J Open Source Softw, 4, 33, 1143, 2019 · doi:10.21105/joss.01143 |
| [38] | Duan, T.; Anand, A.; Ding, DY, NGBoost: natural gradient boosting for probabilistic prediction, International Conference on Machine Learning, 2690-2700, 2020, PMLR |
| [39] | Žilinskas, A.; Calvin, J., Bi-objective decision making in global optimization based on statistical models, J Global Optim, 74, 599-609, 2019 · Zbl 1432.90128 · doi:10.1007/s10898-018-0622-5 |
| [40] | Yang, S.; Pancras, J.; Song, YA, Broad or exact? Search ad matching decisions with keyword specificity and position, Decis Support Syst, 143, 113491, 2021 · doi:10.1016/j.dss.2021.113491 |
| [41] | Ramaboa, KK; Fish, P., Keyword length and matching options as indicators of search intent in sponsored search, Inf Process Manage, 54, 2, 175-183, 2018 · doi:10.1016/j.ipm.2017.11.003 |
| [42] | Zhang W, Yuan S, Wang J et al (2014) Real-time bidding benchmarking with iPinYou dataset. Preprint at arXiv:1407.7073 |
| [43] | Chapelle O (2014) Modeling delayed feedback in display advertising. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp 1097-1105. doi:10.1145/2623330.2623634 |
| [44] | Vernade C, Cappé O, Perchet V (2017) Stochastic bandit models for delayed conversions. Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence. https://hal.science/hal-01545667 |
| [45] | Yang X, Li Y, Wang H et al (2019) Bid optimization by multivariable control in display advertising. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp 1966-1974. doi:10.1145/3292500.3330681 |
| [46] | He Y, Chen X, Wu D et al (2021) A unified solution to constrained bidding in online display advertising. Proceedings of the 27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp 2993-3001. doi:10.1145/3447548.3467199 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
