Journal of Management and Science
Vol. 16 No. 2 (2026): Vol 16 Iss 2 Year 2026
Articles

Artificial Intelligence Tools Used in Consumer Behavior Modeling for Personalized Digital Marketing Strategies

PDF
  • R. Kumaresan,
  • Mrs. Smaila. I
R. Kumaresan
Associate professor and Head Department of Commerce CA, PPG college of arts and science Coimbatore, Tamilnadu, India.
Mrs. Smaila. I
Research scholar, Department of Commerce, PPG college of arts and science, Coimbatore, Tamilnadu, India.
DOI: https://doi.org/10.26524/jms.16.20
Published June 30, 2026
Keywords
  • Artificial Intelligence, Consumer Behavior Modeling, Personalized Marketing, Machine Learning, Predictive Analytics, Customer Lifetime Value, Brand Fidelity, Data Privacy.
How to Cite
R. Kumaresan, & Mrs. Smaila. I. (2026). Artificial Intelligence Tools Used in Consumer Behavior Modeling for Personalized Digital Marketing Strategies. Journal of Management and Science, 16(2), 52-58. https://doi.org/10.26524/jms.16.20

Abstract

In the contemporary digital economy, traditional broad-spectrum and static segmented marketing approaches are rapidly yielding to hyper-personalized computational strategies driven by Artificial Intelligence (AI). This empirical study investigates the strategic integration of sophisticated machine learning models, predictive sequence learning, and natural language processing (NLP) architectures to model, decipher, and anticipate nuanced consumer behavior profiles. Using longitudinal and experimental tracking data gathered from an active universe of e-commerce consumers (N = 450) over a continuous 90-day multi-channel observation window, this paper evaluates the strategic impacts of algorithmic agility and data liquidity on customer acquisition friction, dynamic engagement latency, and conversion probability parameters. Structural Equation Modeling (SEM) conducted via AMOS demonstrates that the deployment of predictive AI architectures optimized with behavioral feedback loops exerts a powerful, statistically significant positive influence on digital brand fidelity (Beta = 0.44, p < 0.001), validating a 24.5% net increase in consumer retention compared to rule-based legacy controls. Furthermore, empirical results confirm that high levels of algorithmic personalization depth are heavily moderated by explicit consumer privacy trust; optimization frameworks suffer immediate efficacy drops when data transparency protocols are obscured. By bridging technical computer science paradigms with psychological consumer behavior constructs, this article resolves the long-standing operational silos between conversion mechanics and long-term customer lifetime value (CLV). Ultimately, this study provides an empirically validated, operational blueprint for contemporary marketing executives and scholars seeking to maximize overall digital return on investment (ROI) while responsibly navigating systemic privacy boundaries.

PDF

Downloads

Download data is not yet available.