Year: 2025
Type: conference-paper
Abstract: This study presents an LLM-driven multi-agent framework designed to enhance email marketing effectiveness through Agentic AI-based personalization. The framework integrates specialized autonomous agents that generate, engage, and evaluate by generating marketing emails that specifically cater to the unique traits of different customer personas that are profiled through segmentation. LLM-powered persona modeling is used to simulate engagement responses and predict performance indicators as KPI indicators (open rates and click-through rates and conversion rates). Unlike traditional A/B testing, the LLM-driven engagement scoring model can enable pre-deployment optimization by estimating email effectiveness through persona-based simulations. Experimental results demonstrate that AI-personalized emails consistently outperform their non-personalized counter-parts. The study reveals how Agentic AI provides promising opportunities for email marketing advancements and LLM-driven engagement modeling in transforming scalable, data-driven email marketing strategies.
Source: MATEC Web of Conferences
Authors: G. Venkatasubramaniam, George Ghinea, Kate Hone, Yongmin Li
Institution: Brunel University of London
Language: English
Subfield: Sociology and Political Science
Field: Social Sciences
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W4414708357