Traditional attribution models struggle to accurately represent the intricate, multi-touchpoint customer journeys typ- ical of contemporary influencer marketing campaigns, especially in the Fast-Moving Consumer Goods (FMCG) sector, where brief purchase cycles and impulsive buying behaviors present distinct measurement difficulties. Three major problems with current methods are: they can’t tell the difference between real campaign impact and random correlations, they don’t handle cross-platform customer journey fragmentation well, and they don’t find a balance between measuring short-term sales and building long-term brand equity. This research introduces a comprehensive five-layer artificial intelligence architecture that integrates Long Short-Term Memory (LSTM) neural networks with attention mechanisms for sequential customer journey modeling, causal inference engines for distinguishing genuine campaign effects from external factors, and multi-objective optimization algorithms that concurrently maximize return on investment while maintaining brand-building objectives. The suggested method combines real-time data from many sources, such as social media APIs, e-commerce transaction logs, brand perception surveys, and competitive intelligence systems, with advanced machine learning processing layers that use computer vision and natural language processing to analyze content per- formance, graph neural networks to group influencers, and real-time scoring engines and budget allocation logic to make decisions automatically. Validation via synthetic control methods and counterfactual analysis guarantees measurement precision while mitigating the endogeneity bias seen in conventional attri- bution methodologies. The architecture offers substantial benefits over traditional models by supplying detailed, touchpoint-level attribution insights with temporal dependency modeling, facilitat- ing automated campaign optimization through real-time budget reallocation based on performance thresholds, and merging quantitative conversion metrics with qualitative brand equity indicators. This all-encompassing method fills the important gap between academic attribution theory and the needs of real-world FMCG marketing, providing a scalable framework for optimizing influencer marketing based on evidence that balances short-term performance with long-term brand building goals.

Influencer marketing attribution,, LSTM neural networks, causal inference, multi-objective optimization, FMCG brand building, real-time marketing optimization, customer jour- ney analytics, marketing mix modeling, artificial intelligence in marketing, data-driven decision making

Y. K. Dwivedi, E. Ismagilova, D. L. Hughes, J. Carlson, R. Filieri, J. Jacobson, V. Jain, H. Karjaluoto, H. Kefi, A. S. Krishen, V. Kumar, M. M. Rahman, R. Raman, P. A. Rauschnabel, J. Rowley, J. Salo, G. A. Tran, and Y. Wang, “Setting the future of digital and social media marketing research: Perspectives and research propositions,” International Journal of Information Management, vol. 59, p. 102168, 2021.

A. Narassiguin and S. Sargent, “Data science for influencer mar- keting: feature processing and quantitative analysis,” arXiv preprint arXiv:1906.05911, 2019.

V. Thangavel, “Revolution of ai in hyper-personalization marketing of fmcg,” 2024, st. Francis Institute of Management and Research, Mumbai, India.

S. Maheswari, “The transformative power of ai in marketing fmcg,” International Journal for Multidisciplinary Research (IJFMR), vol. 5, no. 3, pp. 1–8, May–June 2023, article ID: IJFMR23033760. [Online]. Available: https://www.ijfmr.com

A. Gracias, A. Olukemi, and C. Bell, “Influencer marketing roi: Measure- ment techniques and optimization strategies,” unpublished manuscript.

R. Haider, M. F. I. Shaif, R. Ahmed, N. H. Nafi, M. R. Sumon, and M. Rahman, “Assessing the impact of influencer marketing on brand value and business revenue: An empirical and thematic analysis,” International Journal of Science and Research Archive, vol. 16, no. 2, pp. 471–482, 2025. [Online]. Available: https://clok.uclan.ac.uk/id/eprint/56648/

B. Libai, A. Babic´ Rosario, M. Beichert, B. Donkers, M. Haenlein, R. Hofstetter, P. K. Kannan, R. van der Lans, A. Lanz, H. A. Li, D. Mayzlin, E. Muller, D. Shapira, J. Yang, and L. Zhang, “Influencer marketing unlocked: Understanding the value chains driving the creator economy,” Journal of the Academy of Marketing Science, vol. 53, pp. 4–28, 2025.

A. El Badaoui, “Impact of social media marketing on the perfor- mance of fast-moving consumer goods firms,” 2023, available at SSRN: https://ssrn.com/abstract=4486442.