Attribution of Customers’ Actions Based on Machine Learning Approach

Kadyrov, Timur and Ignatov, Dmitry I. (2019): Attribution of Customers’ Actions Based on Machine Learning Approach. Published in: CEUR Workshop Proceedings , Vol. 2479, (26 September 2019): pp. 77-88.

Abstract

A multichannel attribution model based on gradient boost-ing over trees is proposed, which was compared with the state of theart models: bagged logistic regression, Markov chains approach, shapelyvalue. Experiments on digital advertising datasets showed that the pro-posed model is better than the solutions considered by ROC AUC metric.In addition, the problem of probability prediction of conversion by theconsumer using the ensemble of the analyzed algorithms was solved,the meta-features obtained were enriched with consumers and offlineactivities of the advertising campaign data.

• Item Type: MPRA Paper
• Language: English
• Keywords: Multi-touch attribution; Gradient boosting; Digital advertising; Data-driven marketing
• Subjects: C - Mathematical and Quantitative Methods > C4 - Econometric and Statistical Methods: Special Topics > C45 - Neural Networks and Related Topics; M - Business Administration and Business Economics ; Marketing ; Accounting ; Personnel Economics > M3 - Marketing and Advertising > M31 - Marketing

References

The volume of advertising in its distribution media in 2017.https://www.akarussia.ru/knowledge/market_size/id8180– Official website of the Associ-ation of Communication Agencies of Russia (2017), [Online; last accessed 30-Sep-2019]

The Official Blog of Kaggle.com.http://blog.kaggle.com/tag/xgboost(2019),[Online; last accessed 30-Sep-2019]

The volume of advertising in the means of its distribution in the first half of 2019.http://www.akarussia.ru/knowledge/market_size/id8955– Official website ofthe Association of Communication Agencies of Russia (2019), [Online; last accessed30-Sep-2019]

Amini, M., Truong, T., Goutte, C.: A boosting algorithm for learning bi-partite ranking functions with partially labeled data. In: Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Develop-ment in Information Retrieval, SIGIR 2008, Singapore, July 20-24, 2008. pp.99–106 (2008). https://doi.org/10.1145/1390334.1390354,https://doi.org/10.1145/1390334.1390354

Anderl, E., Becker, I., von Wangenheim, F., Schumann, J.H.: Mapping the cus-tomer journey: A graph-based framework for online attribution modeling (2014)

Dalessandro, B., Perlich, C., Stitelman, O., Provost, F.: Causally moti-vated attribution for online advertising. In: Proceedings of the Sixth In-ternational Workshop on Data Mining for Online Advertising and In-ternet Economy. pp. 7:1–7:9. ADKDD ’12, ACM, New York, NY, USA (2012). https://doi.org/10.1145/2351356.2351363,http://doi.acm.org/10.1145/2351356.2351363

van Eeden, E., Chow, W.: Perspectives from the Global Entertainment & Me-dia Outlook 2019–2023.https://www.pwc.com/gx/en/industries/tmt/media/outlook.html(2019), [Online; last accessed 30-Sep-2019]

Ignatov, D.I., Kuznetsov, S.O., Poelmans, J.: Concept-based biclustering for in-ternet advertisement. In: 12th IEEE International Conference on Data Min-ing Workshops, ICDM Workshops, Brussels, Belgium, December 10, 2012. pp.123–130 (2012). https://doi.org/10.1109/ICDMW.2012.100,https://doi.org/10.1109/ICDMW.2012.100

Lovett, J.: Attribution Methods and Models: A Marketers Framework. Web Ana-lytics Demystified, Inc.http://media.dmnews.com/documents/52/attribution_methods_and_models_12971.pdf(2014), [Online; last accessed 30-Sep-2019]

Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions.In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan,S., Garnett, R. (eds.) Advances in Neural Information Processing Systems 30,pp. 4765–4774. Curran Associates, Inc. (2017),http://papers.nips.cc/paper/7062-a-unified-approach-to-interpreting-model-predictions.pdf

Schapire, R.E.: The strength of weak learnability. Machine Learning5, 197–227 (1990). https://doi.org/10.1007/BF00116037,https://doi.org/10.1007/BF0011603712.

Shao, X., Li, L.: Data-driven multi-touch attribution models. In: Proceed-ings of the 17th ACM SIGKDD International Conference on Knowledge Dis-covery and Data Mining, San Diego, CA, USA, August 21-24, 2011. pp.258–264 (2011). https://doi.org/10.1145/2020408.2020453,https://doi.org/10.1145/2020408.2020453

Shapley, L.S.: A value for n-person games. Contributions to the Theory of Games2(28), 307–317 (1953)

Valizadegan, H., Jin, R., Zhang, R., Mao, J.: Learning to rank by opti-mizing NDCG measure. In: Advances in Neural Information Processing Sys-tems 22: 23rd Annual Conference on Neural Information Processing Sys-tems 2009. Proceedings of a meeting held 7-10 December 2009, Vancouver,British Columbia, Canada. pp. 1883–1891 (2009),http://papers.nips.cc/paper/3758-learning-to-rank-by-optimizing-ndcg-measure

Wolpert, D.H.: Stacked generalization. Neural Networks5(2), 241–259(1992). https://doi.org/10.1016/S0893-6080(05)80023-1,https://doi.org/10.1016/S0893-6080(05)80023-1

Zhang, Y., Wei, Y., Ren, J.: Multi-touch attribution in online advertisingwith survival theory. In: 2014 IEEE International Conference on Data Min-ing, ICDM 2014, Shenzhen, China, December 14-17, 2014. pp. 687–696 (2014).https://doi.org/10.1109/ICDM.2014.130,https://doi.org/10.1109/ICDM.2014.130