AI-Enhanced Marketing Mix Modeling: Integrating ML, XAI, and LLMs for GreaterAccuracy, Interpretability, and Actionability

This paper proposes an AI-enhanced Marketing Mix Modeling (MMM) framework that integrates machinelearning (ML), explainable AI (XAI), and large language models (LLMs) to evaluate marketing effectiveness withimproved predictive accuracy, interpretability, and practical applicability. Moving beyond traditional MMMapproaches, the framework employs the XGBoost algorithm to capture nonlinear relationships between multichannelmarketing investments and business outcomes. SHAP analysis further enhances model interpretability throughfeature-importance rankings, beeswarm visualizations, and dependence plots that quantify each channel’s marginalcontribution. In addition, a Claude-based LLM module translates complex model outputs into natural-languageperformance insights and budget allocation recommendations, lowering technical barriers and improving decision-making actionability. Experimental results demonstrate that, compared with an OLS baseline, the XGBoost modelsignificantly improves predictive performance, increasing R² from 0.8572 to 0.9123 while reducing RMSE and MAEby 21.7% and 22.8%, respectively. The integrated SHAP and LLM components further elucidate channel impacts andsuggest budget optimization strategies, yielding an estimated 18–25% improvement in marketing ROI. Overall, theproposed AI-enhanced MMM framework democratizes advanced marketing analytics by providing businesses withan accessible, automated solution that guides strategic marketing decision-making, enables efficient resourceallocation, and improves marketing returns.