EURO 2024 Copenhagen
Abstract Submission

EURO-Online login

2701. AI meets Sustainability: Using Digital Twins to Leverage Reinforcement Learning – Based Dynamic Pricing in Circular Markets under Competition

Invited abstract in session TA-59: Learning and pricing, stream Pricing and Revenue Management.

Tuesday, 8:30-10:00
Room: S08 (building: 101)

Authors (first author is the speaker)

1. Rainer Schlosser
Hasso Plattner Institute, University of Potsdam

Abstract

Nowadays, customers as well as retailers look for increased sustainability. Recommerce markets - which offer the opportunity to trade-in and resell used products - are constantly growing and help to use resources more efficiently. To manage the additional prices for the trade-in and the resell of used product versions challenges retailers as substitution and cannibalization effects have to be taken into account. An unknown customer behavior as well as competition with other merchants regarding both sales and buying back resources further increases the problem's complexity. Reinforcement learning (RL) algorithms offer the potential to deal with such tasks. However, before being applied in practice, self-learning algorithms need to be tested synthetically to examine whether and which work in different market scenarios. We evaluate and compare different state-of-the-art RL algorithms within a recommerce market simulation framework. We find that RL agents outperform rule-based benchmark strategies in duopoly and oligopoly scenarios. Further, we investigate the competition between RL agents via self-play and study how performance results are affected if more or less information is observable. Using an ablation study, we test the influence of various model parameters and infer managerial insights. Finally, to be able to apply self-learning agents in practice, we show how to calibrate synthetic test environments (digital twins) from data to be used for effective pre-training.

Keywords

Status: accepted

Back to the list of papers