Abstract

Traditional marketing attribution models rely heavily on correlational analysis and are susceptible to over-attributions of conversion to the last touching point. The outcome is wasted budget spending and suboptimal marketing efforts. Recent causal inference study focuses on the determination of single channel effects and neglects the dependence among the effects from multi-channels and the effects of time. This research presents a machine learning powered causal inference method which integrates propensity score estimation, uplift modeling and longitudinal data analysis for multi-channel marketing effectiveness. The proposed approach models cross-channel interactions, revealing solicitations between social media, Email Campaigns, and PPC Ads and the lagged efficacy of marketing. Evidence shows a budget discrepancy of up to 30% in traditional attribution models that overestimate direct-response channels. The findings underline the importance of causal inference-driven marketing analytics that creates a more data-informed basis for budget allocation, campaign planning and campaign performance evaluation in a hypercompetitive environment.

References

• Abhishek, V., Fader, P. S., & Hosanagar, K. (2012). Media exposure through the funnel: A model of multi-stage attribution. Marketing Science, 33(1), 1-20.
• Angrist, J. D., & Pischke, J. S. (2009). Mostly harmless econometrics: An empiricist's companion. Princeton University Press.
• Athey, S., & Imbens, G. (2017). The state of applied econometrics: Causality and policy evaluation. Journal of Economic Perspectives, 31(2), 3-32.
• Bertrand, M., Duflo, E., & Mullainathan, S. (2004). How much should we trust differences-in-differences estimates? Quarterly Journal of Economics, 119(1), 249-275.
• Chernozhukov, V., Chetverikov, D., Demirer, M., Duflo, E., Hansen, C., & Newey, W. (2018). Double machine learning for treatment and causal parameters. Econometrics Journal, 21(1), C1-C68.
• Dalessandro, B., Perlich, C., Stitelman, O., & Provost, F. (2012). Causally motivated attribution for online advertising. Proceedings of the Sixth International Workshop on Data Mining for Online Advertising and Internet Economy.
• De Haan, E., Wiesel, T., & Pauwels, K. (2016). The effectiveness of different forms of online advertising for purchase conversion in a multiple-channel attribution framework. International Journal of Research in Marketing, 33(3), 491-507.
• Gutierrez, P., & Gérardy, J. Y. (2017). Causal Inference and Uplift Modeling in Marketing. Proceedings of Machine Learning Research.
• He, R., & Rao, A. (2024). Causal Inference Methods and Applications in Marketing. Now Publishers.
• Hitsch, G. J., & Misra, S. (2018). Estimating discrete choice models of demand using machine learning methods. Marketing Science, 37(2), 234-256.
• Huber, J. (2024). Causal Machine Learning in Marketing. International Journal of Business and Marketing Science.
• Imbens, G. W., & Rubin, D. B. (2015). Causal inference in statistics, social, and biomedical sciences. Cambridge University Press.
• Li, H., & Kannan, P. K. (2014). Attributing conversions in a multichannel online marketing environment: An empirical model and a field experiment. Journal of Marketing Research, 51(1), 40-56.
• Li, S., Sun, B., & Montgomery, A. L. (2020). Cross-channel spillover effects of online and offline advertising. Management Science, 66(1), 171-189.
• Lewis, R. A., & Rao, J. M. (2015). The unfavorable economics of measuring the returns to advertising. Quarterly Journal of Economics, 130(4), 1941-1973.