Abstract
In this study, we estimate the causal effect of direct promotional email advertising when an RCT could not be performed by only using observational data from a Japanese electronics store. To do so, we build two models for two different types of direct promotional email under a causal inference framework and estimate the treatment effect using the traditional method like propensity score weighting and framework combined with machine learning estimators like meta-learner. The estimated results in our two models show the positive advertising effects of two kinds of direct promotional emails sent by the electronics store. We find that the targeting policy may affect the success of causal inference modeling due to the different difficulties in identifying confounder variables during modeling between the targeting strategy is clear and not. We also find that the electronics store could increase its direct email advertising effects by changing its targeting strategy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Customers who had not bought any PC-related product in the past year before sending the promotional email.
- 2.
Compared to regular membership 1% more extra points for purchases. The annual average fee is 1,078 yen, but it will be free if you make a purchase once a year.
References
Ling, C.X., Li, C.: Data mining for direct marketing: Problems and solutions. In: Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining, pp. 73–79. AAAI Press (1998)
Desai, D.M.: Digital marketing: A review. International Journal of Trend in Scientific Research and Development Special Issue(Special Issue-FIIIIPM2019), pp. 196–200 (2019)
Mehralian, M.M., Khazaee, P.: Effect of digital marketing on the business performance of msmes during the covid-19 pandemic: The mediating role of customer relationship management. SSRN Electronic Journal (2022), https://ssrn.com/abstract=4195985
Corona disaster’s digital marketing implementation effectiveness revealed - adobe survey (Dec 2021). https://japan.zdnet.com/article/35180445/ Accessed 2 May 2022
Ellickson, P.B., Kar, W., Reeder, J.C.: Estimating marketing component effects: Double machine learning from targeted digital promotions. Marketing Science 0(0) (2022). https://doi.org/10.1287/mksc.2022.1401
Johnson, G.: Inferno: A guide to field experiments in online display advertising. SSRN Electronic Journal (2020). https://ssrn.com/abstract=3581396
Tutorial on causal inference and its connections to machine learning (using dowhy+econml). https://www.pywhy.org/dowhy/v0.8/tutorial-causalinference-machinelearning-using-dowhy-econml.html, Accessed 2 May 2022
Heckman, J.J., Vytlacil, E.J.: Chapter 70 econometric evaluation of social programs, part i: Causal models, structural models and econometric policy evaluation. Handbook of Econometrics, pp. 4779–4874 (2007)
Dehejia, R.H., Wahba, S.: Propensity score-matching methods for nonexperimental causal studies. Rev. Econ. Stat. 84(1), 151–161 (2002)
Künzel, S.R., Sekhon, J.S., Bickel, P.J., Yu, B.: Metalearners for estimating heterogeneous treatment effects using machine learning. Proc. Natl. Acad. Sci. 116(10), 4156–4165 (2019)
Rosenbaum, P.R., Rubin, D.B.: The central role of the propensity score in observational studies for causal effects. Biometrika 70(1), 41–55 (1983)
Sharma, A., Kiciman, E.: Dowhy: An end-to-end library for causal inference (2020). https://arxiv.org/abs/2011.04216
Alaa, A., van der Schaar, M.: Limits of estimating heterogeneous treatment effects: Guidelines for practical algorithm design. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, 80, pp. 129–138 (10–15 Jul 2018), https://proceedings.mlr.press/v80/alaa18a.html
Künzel, S.R., Sekhon, J.S., Bickel, P.J., Yu, B.: Metalearners for estimating heterogeneous treatment effects using machine learning. Proc. Natl. Acad. Sci. 116(10), 4156–4165 (2019)
Nie, X., Wager, S.: Quasi-oracle estimation of heterogeneous treatment effects (2017), https://arxiv.org/abs/1712.04912
About causal ml. https://causalml.readthedocs.io/en/latest/about.html Accessed 2 May 2022
Validation. https://causalml.readthedocs.io/en/latest/validation.html Accessed 2 May 2022
Imbens, G.W., Wooldridge, J.M.: Recent developments in the econometrics of program evaluation. J. Econ. Lit. textbf47(1), pp. 5–86 (March 2009). https://www.aeaweb.org/articles?id=10.1257/jel.47.1.5
CustomerGauge: NPS &CX BENCHMARK REPORT (2018)
Gordon, B.R., Moakler, R., Zettelmeyer, F.: Close enough? a large-scale exploration of non-experimental approaches to advertising measurement. Marketing Science 0(0) (2022), https://doi.org/10.1287/mksc.2022.1413
Acknowledgment
We thank an electoronical retail campany of Japan for permission to use valuable datasets. This work was supported by JSPS KAKENHI Grant Number 21H04600 and 21K13385.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ma, Y., Otake, K., Namatame, T. (2023). Causal Inference of Direct Email Advertising Effects Using ID-POS Data of an Electronics Store. In: Coman, A., Vasilache, S. (eds) Social Computing and Social Media. HCII 2023. Lecture Notes in Computer Science, vol 14025. Springer, Cham. https://doi.org/10.1007/978-3-031-35915-6_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-35915-6_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35914-9
Online ISBN: 978-3-031-35915-6
eBook Packages: Computer ScienceComputer Science (R0)