Analysis of attributional modeling methods in marketing


如何引用文章

全文:

开放存取 开放存取
受限制的访问 ##reader.subscriptionAccessGranted##
受限制的访问 订阅或者付费存取

详细

The sharp increase in the number of Internet users has led to the rapid spread of e-commerce, and, as a result, the development of online (digital) marketing tools. At the same time, one of the key tasks is to estimate the impact on the user of each marketing touchpoint in the «digital path» when the user reaches a certain goal (conversion). In other words, it is required to assess the extent to which each marketing channel contributes to the success of the marketing strategy, which is traditionally solved by applying an attribution model. In recent years, with the development of technologies for collecting, accumulating, and aggregating web data about users and their interactions with digital marketing channels, approaches to attribution modeling have also improved. Researchers have proposed a wide range of approaches to attribution modeling, and the question of the best approach is still relevant today. The following tasks are set and solved in the article: 1) the concept of «attribution modeling» is defined; 2) modern methods of attribution modeling are presented and described; 3) identified and described the advantages and disadvantages of each approach to attribution modeling.

全文:

受限制的访问

作者简介

Igor Denisenko

Financial University under the Government of the Russian Federation

Email: iadenisenko2020@edu.fa.ru
Postgraduate student, department of data analysis and machine learning Moscow, Russian Federation

Natalia Grineva

Financial University under the Government of the Russian Federation

Email: ngrineva@fa.ru
Cand. Sci. (Econ.), Associate Professor, Associate Professor of the Department of analysis, decision making and financial technology Moscow, Russian Federation

参考

  1. Anderl E. Mapping the customer journey: Lessons learned from graph-based online attribution modeling. / Anderl E , Becker I., Von Wangenheim F., Schumann J.H. // International Journal of Research in Marketing. - 2016. -P. 457-474.
  2. Arava, S.K., Dong, C., Yan, Z., & Pani, A. Deep neural net with attention for multi-channel multi-touch attribution. / - 2018.arXiv preprint arXiv:1809.02230.
  3. Archak N., Vahab S. Mirrokni, and S. Muthukrishnan: Mining Advertiser-Specific User Behavior Using Adfactor // WWW 2010.
  4. Berman R. Beyond the last touch: Attribution in online advertising. / Berman R. // Marketing Science. - 2018. - P. 771-792.
  5. Danaher P., Van Heerde H. Delusion in attribution: Caveats in using attribution for multimedia budget allocation. // Journal of Marketing Research. - 2018. - P.667-685
  6. Dalessandro B, Claudia Perlich, Ori Stitelman, and Foster Provost: Causally Motivated Attribution for Online Advertising. // M6D Research. - 2012.
  7. Kotler P.: Marketing management: The millennium edition. // 1999
  8. Li, H., & Kannan P.K. Attributing conversions in a multichannel online marketing environment: An empirical model and a field experiment. // Journal of Marketing Research. - 2014.
  9. Sebastian Cano Berlanga, Cori Vilella, et al. Attribution models and the cooperative game theory
  10. Shao, Xuhui and Lexin Li : Data-Driven Multi-Touch Attribution Models // 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining: ACM, - 2011 258-264.
  11. Shapley L. A value for n-person games. / Shapley L. // Contributions to the Theory of Games. - 1953. - P.307-317.
  12. Vilma T.: Towards a Digital Attribution Model: Measuring the Impact of Display Advertising on Online Consumer Behavior // SSRN Electronic Journal. - 2015
  13. https://www.akarussia.ru/knowledge/market_size/id8180
  14. https://support.google.com/analytics/answer/1665189?hl=ru
  15. https://www.emarketer.com/Article/Attribution-Becoming-More-of-Priority-Marketers/1014286

补充文件

附件文件
动作
1. JATS XML


##common.cookie##