Abstract
AI-powered personalization systems have enhanced digital services by increasing user engagement, retention, and conversions. However, performance-maximizing personalization approaches compromise privacy, increase bias, and decrease transparency. This article uses a multipurpose personalization system that can simultaneously increase engagement and uphold ethics using Festinger's Social Comparison Theory and Skinner's Reinforcement Theory. The system consists of social comparison-based personalization modules, reinforcement learning, and an ethics-focused system layer for re-ranking, explainability, and privacy-preserving re-learning assumptions. The system's performance is validated using Python simulations for 1.2 million customer-level interaction data, showing improved proxy transparency and reduced equality in exposure bias with unchanged engagement performance. The research explains and creates the Ethical Experience Index (EEI), a measure of both engagement and ethics performance experiences for a systematic evaluation and comparison of performance. The results show the potential of integrating ethics systems for personalization that provide a repeatable, theory-based approach to ethics and AI-driven personalization based on simulations.
References
Acquisti, Alessandro, Laura Brandimarte, and George Loewenstein. "Privacy and human behavior in the age of information." Science 347, no. 6221 (2015): 509-514.
Soni, Vishvesh. "AI and the Personalization-Privacy Paradox: Balancing Customized Marketing with Consumer Data Protection." International Journal of Computer Trends and Technology 72, no. 9 (2024): 24-31.
Binns, Reuben. "Fairness in machine learning: Lessons from political philosophy." In Conference on fairness, accountability and transparency, PMLR, 2018. 149-159.
Cadwalladr, C. and Graham-Harrison, E. (2018) ‘The Cambridge Analytica files: The story that revealed Facebook’s darkest secret’, The Guardian, 17 March. Available at: https://www.theguardian.com/news/series/cambridge-analytica-files
Doshi-Velez, Finale, and Been Kim. "Towards a rigorous science of interpretable machine learning." arXiv preprint arXiv:1702.08608 (2017).
Festinger, L. (1954) ‘A theory of social comparison processes’, Human Relations, 7(2). 117–140.
Floridi, Luciano, Josh Cowls, Thomas C. King, and Mariarosaria Taddeo. "How to design AI for social good: Seven essential factors." In Ethics, governance, and policies in artificial intelligence, Cham: Springer International Publishing, 2021. 125-151.
Gomez-Uribe, Carlos A., and Neil Hunt. "The netflix recommender system: Algorithms, business value, and innovation." ACM Transactions on Management Information Systems (TMIS) 6, no. 4 (2015): 1-19.
Huang, Ming-Hui, and Roland T. Rust. "Engaged to a robot? The role of AI in service." Journal of Service Research 24, no. 1 (2021): 30-41.
Turlapati, Venkata Ramaiah, P. Vichitra, N. Raval, J. Khaja Mohinuddeen, and B. R. Mishra. "Ethical Implications of Artificial Intelligence in Business Decision-making: A Framework for Responsible AI Adoption." Journal of Informatics Education and Research 4, no. 1 (2024).
Skinner, B.F. (1953) Science and Human Behavior. New York: Macmillan.
Chandra, Shobhana, Sanjeev Verma, Weng Marc Lim, Satish Kumar, and Naveen Donthu. "Personalization in personalized marketing: Trends and ways forward." Psychology & Marketing 39, no. 8 (2022): 1529-1562.
Voigt, Paul, and Axel Von dem Bussche. "The eu general data protection regulation (gdpr)." A practical guide, 1st ed., Cham: Springer International Publishing 10, no. 3152676 (2017): 10-5555.
Vallabhaneni, Anirudh Sai, Anjali Perla, Revanth Reddy Regalla, and Neelam Kumari. "The power of personalization: AI-driven recommendations." In Minds Unveiled, pp. 111-127. Productivity Press, 2024.