The Reserve Price Optimization for Publishers on Real-Time Bidding on-Line Marketplaces with Time-Series Forecasting

• Autorzy: Andrzej Wodecki
• Języki publikacji: EN

Abstrakty

EN

Today's Internet marketing ecosystems are very complex, with many competing players, transactions concluded within milliseconds, and hundreds of different parameters to be analyzed in the decision-making process. In addition, both sellers and buyers operate under uncertainty, without full information about auction results, purchasing preferences, and strategies of their competitors or suppliers. As a result, most market participants strive to optimize their trading strategies using advanced machine learning algorithms. In this publication, we propose a new approach to determining reserve-price strategies for publishers, focusing not only on the profits from individual ad impressions, but also on maximum coverage of advertising space. This strategy combines the heuristics developed by experienced RTB consultants with machine learning forecasting algorithms like ARIMA, SARIMA, Exponential Smoothing, and Facebook Prophet. The paper analyses the effectiveness of these algorithms, recommends the best one, and presents its implementation in real environment. As such, its results may form a basis for a competitive advantage for publishers on very demanding online advertising markets. (original abstract)

Słowa kluczowe

EN

e-marketing; Internet advertising; Machine learning; Pricing strategies; Forecasting

PL

Marketing internetowy; Reklama w internecie; Uczenie maszynowe; Strategia cen; Prognozowanie

• Czasopismo: Foundations of Management
• Rocznik: 2020
• Tom: 12
• Numer: nr 1
• Strony: 167--180

Twórcy

autor

Andrzej Wodecki

• Warsaw University of Technology, Poland

Bibliografia

• Anon, 2020a. Ad Exchange historical report - Google Ad Manager Help. [online] Available at: < https://support.google.com/admanager/table/7612037?hl=en) > [Accessed 10 Jun. 2020].
• Anon, 2020b. Autoregressive integrated moving average. In: Wikipedia. [online] Available at: < https://en.wikipedia.org/w/index.php?title=Autoregressive_integrated_moving_average&oldid=950625193 > [Accessed 1 Jun. 2020].
• Anon, 2020c. Exponential smoothing. In: Wikipedia. [online] Available at: < https://en.wikipedia.org/w/index.php?title=Exponential_smoothing&oldid=957231778 > [Accessed 1 Jun. 2020].
• Anon, 2020d. Prophet. [online] Prophet. Available at: < http://facebook.github.io/prophet/ > [Accessed 1 Jun. 2020].
• Anon, 2020e. Prophet Diagnostics. [online] Prophet. Available at: < http://facebook.github.io/prophet/docs/diagnostics.html > [Accessed 1 Jun. 2020].
• Austin, A., Barnard, J. and Hutcheon, N., 2019. Programmatic Marketing Forecasts 2019. [online] Zenith. Available at: < https://s3.amazonaws.com/media.mediapost.com/uploads/ProgrammaticMarketingForecasts2019.pdf >.
• Austin, D., Seljan, S., Monello, J. and Tzeng, S., 2016. Reserve Price Optimization at Scale. In: 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA). 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA). pp.528-536.
• Brownlee, J., 2018a. Deep Learning for Time Series Forecasting. [online] Available at: < www.machinelearningmastery.com >.
• Brownlee, J., 2018b. Introduction to Time Series Forecasting in Python. [online] Available at: < www.machinelearningmastery.com >. Cai, H., Ren, K., Zhang, W., Malialis, K., Wang, J., Yu, Y. and Guo, D., 2017. Real-Time Bidding by Reinforcement Learning in Display Advertising. Proceedings of the Tenth ACM International Conference on Web Search and Data Mining - WSDM '17, pp.661-670.
• Chapman, P., Clinton, J., Kerber, R., Khabaza, T., Reinartz, T., Shearer, C. and Wirth, R., 2004. CRISP-DM 1.0. SPSS.
• Choi, H., Mela, C.F., Balseiro, S. and Leary, A., 2019. Online Display Advertising Markets: A Literature Review and Future Directions. SSRN Electronic Journal. [online] Available at: < https://www.ssrn.com/abstract=3070706 > [Accessed 4 May 2020].
• Hipel, K.W. and McLeod, A.I. eds., 1994. Chapter 12 Seasonal Autoregressive Integrated Moving Average Models. In: Developments in Water Science, Time Series Modelling of Water Resources and Environmental Systems. [online] Elsevier. pp.419-462. Available at: < http://www.sciencedirect.com/science/article/pii/S0167564808706737 > [Accessed 10 Jun. 2020].
• Li, J., Ni, X. and Yuan, Y., 2018. The Reserve Price of Ad Impressions in Multi-Channel Real-Time Bidding Markets. IEEE Transactions on Computational Social Systems, 5(2), pp.583-592.
• Li, J., Ni, X., Yuan, Y., Qin, R., Wang, X. and Wang, F.-Y., 2017. The impact of reserve price on publisher revenue in real-time bidding advertising markets. In: 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC). [online] 2017 IEEE International Conference on Systems, Man and Cybernetics (SMC). Banff, AB: IEEE. pp.1256-1261. Available at: < http://ieeexplore.ieee.org/document/8122785/ > [Accessed 7 May 2020].
• Lu, J., Yang, C., Gao, X., Wang, L., Li, C. and Chen, G., 2019. Reinforcement Learning with Sequential Information Clustering in Real-Time Bidding. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management. [online] CIKM '19: The 28th ACM International Conference on Information and Knowledge Management. Beijing China: ACM. pp.1633-1641. Available at: < https://dl.acm.org/doi/10.1145/3357384.3358027 > [Accessed 4 May 2020].
• Makridakis, S., Spiliotis, E. and Assimakopoulos, V., 2018. Statistical and Machine Learning forecasting methods: Concerns and ways forward. PLOS ONE, 13(3), p.e0194889.
• Myerson, R.B., 1981. Optimal Auction Design. Mathematics of Operations Research, 6(1), pp.58-73.
• Radovanovic, A. and Heavlin, W.D., 2012. Riskaware revenue maximization in display advertising. In: Proceedings of the 21st international conference on World Wide Web - WWW '12. [online] the 21st international conference. Lyon, France: ACM Press. pp.91-100. Available at: < http://dl.acm.org/citation.cfm?doid=2187836.2187850 > [Accessed 5 Jun. 2020].
• Ren, K., Qin, J., Zheng, L., Yang, Z., Zhang, W. and Yu, Y., 2019. Deep Landscape Forecasting for Real-time Bidding Advertising. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD '19. [online] the 25th ACM SIGKDD International Conference. Anchorage, AK, USA: ACM Press. pp.363-372. Available at: < http://dl.acm.org/citation.cfm?doid=3292500.3330870 > [Accessed 4 May 2020].
• Riley, J.G. and Samuelson, W.F., 1981. Optimal Auctions. The American Economic Review, 71(3), pp.381-392.
• Wang, J., Zhang, W. and Yuan, S., 2017. Display Advertising with Real-Time Bidding (RTB) and Behavioural Targeting. arXiv:1610.03013 [cs]. [online] Available at: < http://arxiv.org/abs/1610.03013 > [Accessed 11 May 2020].
• Wang, Y., Ren, K., Zhang, W., Wang, J. and Yu, Y., 2016. Functional Bid Landscape Forecasting for Display Advertising. In: European Conference on Machine Learning and Knowledge Discovery in Databases - Volume 9851, ECML PKDD 2016. [online] Riva del Garda, Italy: Springer-Verlag. pp.115-131. Available at: < https://doi.org/10.1007/978-3-319-46128-1_8 > [Accessed 3 Jun. 2020].
• ] Wu, W., Yeh, M.-Y. and Chen, M.-S., 2018. Deep Censored Learning of the Winning Price in the Real Time Bidding. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD '18. [online] London, United Kingdom: Association for Computing Machinery. pp.2526-2535. Available at: < https://doi.org/10.1145/3219819.3220066 > [Accessed 3 Jun. 2020].
• ] Wu, W.C.-H., Yeh, M.-Y. and Chen, M.-S., 2015. Predicting Winning Price in Real Time Bidding with Censored Data. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '15. [online] Sydney, NSW, Australia: Association for Computing Machinery. pp.1305-1314. Available at: < https://doi.org/10.1145/2783258.2783276 > [Accessed 3 Jun. 2020].
• Yang, C., Lu, J., Gao, X., Liu, H., Chen, Q., Liu, G. and Chen, G., 2020. MoTiAC: Multi-Objective Actor-Critics for Real-Time Bidding. arXiv:2002.07408 [cs]. [online] Available at: < http://arxiv.org/abs/2002.07408 > [Accessed 5 May 2020].

Identyfikatory

DOI

10.2478/fman-2020-0013