Modeling Consumer Adoption of Green Technologies Using Artificial and Deep Neural Networks: Insights from Tamil Nadu, India

Abstract

The accelerating global environmental crisis underscores the urgent need to promote green technologies that support sustainable consumption and responsible production. This study investigates the psychological, social, and technological determinants influencing Green Technology Adoption (GTA) among consumers in Tamil Nadu, India. By integrating behavioral theory with machine learning, the research applies Artificial Neural Networks (ANN) and Deep Neural Networks (DNN) to predict consumer adoption patterns and uncover nonlinear behavioral dynamics. Primary survey data were collected from 350 respondents through a structured questionnaire comprising 32 validated items measured on a five-point Likert scale. Empirical results reveal that eco-label trust, environmental concern, and sustainable purchase intention are the strongest predictors of adoption behavior, while technology readiness and perceived value exert moderate but significant effects. The DNN model demonstrated superior performance (R² = 0.9361) compared to the ANN (R² = 0.5293), indicating its effectiveness in modeling complex, hierarchical consumer cognition. Cluster analysis further identified three distinct consumer segments high, moderate, and low engagement highlighting heterogeneous readiness levels toward sustainability-oriented technologies. The study contributes both methodologically and theoretically by demonstrating how deep learning enhances predictive precision and interpretive depth in behavioral research. Practically, the findings guide policymakers and marketers in designing trust-based communication, improving eco-label credibility, and developing targeted awareness programs to accelerate sustainable technology adoption. The research aligns with the United Nations Sustainable Development Goals (SDGs) 7, 9, and 12, emphasizing clean energy, innovation, and responsible consumption.