Personalized Email Marketing Strategy: A Reinforcement Learning Approach

Authors: Lei Zhang, Tingting Xu, Jun He, Zhenyu Yan, Roger Brooks

Abstract:

Email marketing is one of the most important segments of online marketing. Email content is vital to customers. Different customers may have different familiarity with a product, so a successful marketing strategy must personalize email content based on individual customers’ product affinity. In this study, we build our personalized email marketing strategy with three types of emails: nurture, promotion, and conversion. Each type of emails has a different influence on customers. We investigate this difference by analyzing customers’ open rates, click rates and opt-out rates. Feature importance from response models is also analyzed. The goal of the marketing strategy is to improve the click rate on conversion-type emails. To build the personalized strategy, we formulate the problem as a reinforcement learning problem and adopt a Q-learning algorithm with variations. The simulation results show that our model-based strategy outperforms the current marketer’s strategy.

Keywords: Email marketing, email content, reinforcement learning, machine learning, Q-learning.

References:

[1] R. Ahmed, D. Streimikiene, G. Berchtold, J. Vveinhardt, R. Soomro and Z. Channar, “Effectiveness of Online Digital Media Advertising as A Strategic Tool for Building Brand Sustainability: Evidence from FMCGs and Services Sectors of Pakistan”, Sustainability, vol. 11, pp. 1-40, 2019.
[2] L. Fuxman, H. Elifoglu, C. Chao and T. Li, “Digital Advertising: A More Effective Way to Promote Businesses’ Products”, Journal of Business Administration Research, vol. 3, No. 2, pp. 59 – 67, 2014
[3] M. Merisavo, M. Raulas, “The impact of email marketing on brand loyalty”, Journal of Product and Brand Management, vol 13, No. 7, pp.498-505, 2004.
[4] The Radicati Group, Inc. “Email Statistics Report, 2019-2023”, https://www.radicati.com/wp/wp-content/uploads/2018/12/Email-Statistics-Report-2019-2023-Executive-Summary.pdf
[5] C.H., Cho, H.K., Khang, “The State of Internet-Related Research in Communications, Marketing, and Advertising: 1994-2003”, Journal of Advertising, vol. 35, issue 3, pp.143 – 163, 2006.
[6] Adobe Inc., https://www.adobe.com/creativecloud.html
[7] New Research, “Why do people unsubscribe from email newsletters?”, https://lab.getapp.com/new-research-getdata-why-do-people-unsubscribe-from-email-newsletters/
[8] D.P. Bertsekas, J.N. Tsitsiklis, Neuro-Dynamic Programming, Athena Scientific, 1996
[9] S.Zhang, R.S. Sutton, “A Deeper Look at Experience Replay”, 2017, https://arxiv.org/abs/1712.01275
[10] L. Chittenden and R. Rettie. An evaluation of e-mail marketing and factors affecting response. Journal of Targeting, Measurement and Analysis for Marketing, 11(3):203--217, 2003
[11] R. Gupta, Guanfeng Liang, Hsiao-Ping Tseng, Ravi Kiran Holur Vijay, Xiaoyu Chen, and Romer Rosales, “Email Volume Optimization at LinkedIn”, “22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’16)”, pp.97–106, 2016
[12] K. Yang, J.H. Min, and K. Garza-Baker, “Post-stay email marketing implications for the hotel industry: Role of email features, attitude, revisit intention and leisure involvement level”, Journal of Vacation Marketing, Vol. 25(4) pp.405–417, 2019
[13] K. Jaidka, T. Goyal, N. Chhaya, “Predicting Email and Article Clickthroughs with Domain-adaptive Language Models”, Proceedings of the 10th ACM Conference on web science, pp.177-184, 2018
[14] K. Litinthong, C. Liu, and X. Liu, “An Empirical Study to Understand the Effect of Email Marketing on Consumer’s Online Buying Behavior in a Developing Country, “In Proceedings of the 2019 3rd International Conference on Management Engineering, Software Engineering and Service Sciences, pp. 179–183, 2019
[15] Z. Moshe, T. Don，G. Yuval, “Does color in email make a difference?”, Communications of the ACM，Vol 49, Issue 4, pp. 94-99, 2006
[16] A. L. Micheaux, "Managing E-Mail Advertising Frequency from the Consumer Perspective," Journal of Advertising, vol. 40, (4), pp. 45-65, 2011.
[17] J. W, Christopher and D. Peter, “Q-learning. Machine learning”, vol. 8(3-4), pp. 279–292, 1992
[18] V. Mnih, K. Kavukcuoglu, D. Silver, David, A. Graves, A. Alex, I. Antonoglou, D. Wierstra, M. Riedmiller, Playing Atari with Deep Reinforcement Learning, 2013
[19] H. V. Hasselt, A. Guez, and D. Silver, "Deep reinforcement learning double Q-Learning”, in Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI’16), pp. 2094–2100, 20.