Can AI-Driven Nudging Promote Sustainable Product Adoption on E-Commerce Platforms?

Objective: this study aims to identify effective behavioral interventions and machine learning models that promote eco-friendly purchases. Theoretical approach: the study is grounded in behavioral economics and choice architecture, drawing on Thaler and Sunstein’s nudge theory to explain how subtle digital design elements can guide choices while preserving autonomy. Method: a systematic review was conducted based on the PRISMA framework utilizing multiple academic databases. Studies were analyzed for AI’s role in sustainability marketing, model effectiveness, and ethical considerations. Results: AI-based nudging techniques such as personalization, default green options, social proof, and gamification significantly enhance engagement in sustainable purchasing behavior. Machine learning models like Random Forests, Deep Neural Networks, and Reinforcement Learning play a crucial role in optimizing AI nudging for green consumption. Conclusions: the study highlights the potential of AI nudging in shaping sustainable e-commerce, especially when combined with transparent, bias-aware, and explainable systems. The study contributes by consolidating notable research on AI-driven nudging in sustainable e-commerce, comparing machine learning models for green consumer targeting with explicit attention to performance–explainability tradeoffs, and proposing an experimental design to test their effectiveness and ethics. The study also offers actionable implications for businesses and policymakers by linking AI-powered strategies to Sustainable Development Goals 12 and 13. Businesses and policymakers can leverage ethical AI frameworks to improve trust in sustainability efforts on e-commerce platforms. Future research should focus on real-world AI experiments, interdisciplinary AI frameworks, and ethical AI regulations to ensure responsible AI adoption in e-commerce.