Integration of Artificial Intelligence and Behavioral Economics: Optimizing Consumer Processes and Decisions in Complex Environments

Abstract

This study presents a comprehensive approach that combines artificial intelligence (AI) and behavioral economics to optimize industrial processes and better understand consumer decisions in complex and uncertain environments, such as inflationary contexts. Through a quantitative methodology in two phases, data from 1,200 consumers were analyzed and neural network models were implemented in 50 manufacturing companies in Latin America. In the first phase, cognitive biases such as loss aversion, anchoring effect and availability were evaluated, identifying their significant influence on irrational decisions under economic pressure. In the second, AI algorithms were applied—such as recurrent neural networks and recommendation systems—to improve energy efficiency, reduce cycle times, and optimize inventories. The results show statistically significant increases in production efficiency (t(49) = 9.62, p < 0.001) and an 11.6% improvement in predictive accuracy when integrating behavioral variables into AI models. The conclusions underscore the strategic value of hybrid models for industrial management, prediction of consumption behavior and the design of public policies in high volatility scenarios.