Read the original document by opening this link in a new tab.
Table of Contents
Abstract
Keywords
I. Introduction
II. Background
III. Methodology
A. States
B. Actions
C. Q-value approximation
D. Reward
Conclusion
Summary
This paper discusses the use of Reinforcement Learning techniques for fair dynamic pricing. It addresses the importance of fairness in pricing policies to maintain customer trust and avoid long-term losses for companies. The paper demonstrates how Reinforcement Learning can be utilized to optimize revenue while ensuring fairness in dynamic pricing. By integrating fairness using Jain's index as a metric, the study shows improvements in fairness perception without compromising revenue optimization. The methodology involves defining states, actions, Q-value approximation, and a reward system that balances price optimization with fairness. Experimental results show the effectiveness of the proposed approach in achieving revenue and fairness goals.