Integrating Artificial Intelligence into Lean Marketing Frameworks: A Predictive Model for Minimizing Waste in Customer Acquisition
Integrating Artificial Intelligence into Lean Marketing Frameworks: A Predictive Model for Minimizing Waste in Customer Acquisition
Seyed Mahmoud Hosseini Amiri1 Mohammadreza Kabiri Yeganeh2
1) Department of Business Administration and Information Technology Management, Payame Noor University (PNU), Tehran, Iran E-mail:
2) Department of Business Administration, Qaemshahr Branch, Payame Noor University, Mazandaran, Iran E-mail:
IOI Code
:
ABEB-ACAFDD
Publication :
4th International Conference on Recent Advances in Engineering, Innovation and Technology - Belgium(eitconf.com)
Abstract :
This paper investigates how integrating artificial intelligence with lean marketing principles can minimize waste in the customer acquisition process while maintaining favorable consumer cognitive, affective, and behavioral responses along the journey. Being a review and conceptual study, the paper proceeds in three sections. First, the literature on consumer behavior, lean marketing, and machine learning applications in marketing is reviewed, mapping Ohno’s seven classical wastes to customer acquisition stages. Second, the proposed conceptual model is introduced, wherein AI-driven personalization, response speed, and message relevance exert their effects on purchase intention through trust and perceived value, with privacy concerns acting as a moderating variable. An empirical testing design for this model is also outlined in this section. Third, to demonstrate the modeling logic, a simulated customer acquisition funnel with 24,000 leads is analyzed. In this illustrative sample, the logistic regression model achieved an area under the curve (AUC) of 0.772, and the customer acquisition cost (CAC) decreased by approximately 27.9% compared to contacting all leads, albeit with about 20% of conversions being lost. Because the data are synthetic, these figures do not constitute empirical evidence for any real-world enterprise and serve solely for methodological illustration. The overarching conclusion is that the utility of prediction for waste reduction depends on trust, perceived value, and consumer privacy sensitivity, which must be validated through controlled field experiments.
Keywords : artificial intelligence lean marketing customer acquisition waste predictive modeling consumer behavior privacy concerns