Evaluating The Effectiveness of Online Vs. Offline Advertising Using AI-Based Multi-Touch Attribution Models
Keywords:
AI-based attribution, multi-touch attribution (MTA), online advertising, offline advertising, ROI analysis, marketing analyticsAbstract
In an increasingly fragmented marketing landscape, understanding the contribution of both online and offline advertising touchpoints to conversions has become critical. This study leverages AI-based multi-touch attribution (MTA) models to evaluate and compare the effectiveness of online versus offline advertising channels. Using secondary data from existing campaign datasets and published industry data, we apply a recurrent neural network (RNN) attribution model and a Shapley-value credit allocation mechanism to estimate incremental conversion impacts. We then analyze the relative ROI (return on investment) of online and offline channels. Our results suggest that AI-driven attribution provides a richer, more granular view of touchpoint contributions, uncovering underappreciated offline effects while correcting for bias in rule-based models. We conclude with implications for media budget allocation, limitations, and directions for future research.
References
Du, R., Zhong, Y., Nair, H., Cui, B., & Shou, R. (2019). Causally Driven Incremental Multi Touch Attribution Using a Recurrent Neural Network. arXiv.
Kumar, S., Gupta, G., Prasad, R., Chatterjee, A., Vig, L., & Shroff, G. (2020). CAMTA: Causal Attention Model for Multi-touch Attribution. arXiv.
Li, N., Arava, S. K., Dong, C., Yan, Z., & Pani, A. (2018). Deep Neural Net with Attention for Multi-channel Multi-touch Attribution (DNAMTA). arXiv.
Tang, J. (2024). DCRMTA: Unbiased Causal Representation for Multi-touch Attribution. arXiv.
Ren, K., Fang, Y., Zhang, W., Liu, S., Li, J., Zhang, Y., Yu, Y., & Wang, J. (2018). Learning Multi-touch Conversion Attribution with Dual-attention Mechanisms for Online Advertising. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM). (as discussed in analysis of state-of-the-art approaches) Growth-onomics. (n.d.). 5 AI Attribution Models for Multi-Touch Campaigns. Retrieved from Growth-onomics website. Salesforce. (n.d.). Multi-Touch Attribution: What It Is & Best Practices. Retrieved from Salesforce website. Eliya.io. (n.d.). MMM vs Multi-Touch Attribution: Pros, Cons & When to Use Each. Retrieved from Eliya.io blog.
TopBots. (2020). Novel AI Approaches for Marketing & Advertising. Retrieved from TopBots website. UCL Research. (n.d.). Learning Multi-touch Conversion Attribution — Evaluation Protocol. (Based on their offline evaluation framework.)
Shaikh, S. A., & Jagirdar, A. H. (2026). Beyond AI dependence: Pedagogical approaches to strengthen student reasoning and analytical skills. In S. Khan & P. Pringuet (Eds.), Empowering learners with AI: Strategies, ethics, and frameworks (Chapter 8, pp. 1–16). IGI Global. https://doi.org/10.4018/979-8-3373-7386-7.ch008
Shaikh, S. A. (2024). Empowering Gen Z and Gen Alpha: A comprehensive approach to cultivating future leaders. In Futuristic Trends in Management (IIP Series, Vol. 3, Book 9, Part 2, Chapter 2). IIP Series. https://doi.org/10.58532/V3BHMA9P2CH2
Chougle, Z. S., & Shaikh, S. (2022). To understand the impact of Ayurvedic health-care business & its importance during COVID-19 with special reference to “Patanjali Products”. In Proceedings of the National Conference on Sustainability of Business during COVID-19, IJCRT, 10(1),
Bhagat, P. H., & Shaikh, S. A. (2025). Managing health care in the digital world: A comparative analysis on customers using health care services in Mumbai suburbs and Pune city. IJCRT. Registration ID: IJCRT_216557.
Downloads
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
