Item type:Journal Article,

Self-learning Agents for Recommerce Markets

Loading...
Thumbnail Image

Fulltext URI

Document type

Text/Journal Article

Additional Information

Date

relationships.isAuthorOf

Groeneveld, Jan
Herrmann, Judith
Mollenhauer, Nikkel
Dreeßen, Leonard
Bessin, Nick
Tast, Johann Schulze
Kastius, Alexander
Huegle, Johannes
Schlosser, Rainer

Journal Title

Journal ISSN

Volume Title

Publisher

Springer

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 resale 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 they and which work in different market scenarios. In the paper, the authors evaluate and compare different state-of-the-art RL algorithms within a recommerce market simulation framework. They find that RL agents outperform rule-based benchmark strategies in duopoly and oligopoly scenarios. Further, the authors investigate the competition between RL agents via self-play and study how performance results are affected if more or less information is observable (cf. state components). Using an ablation study, they test the influence of various model parameters and infer managerial insights. Finally, to be able to apply self-learning agents in practice, the authors show how to calibrate synthetic test environments from observable data to be used for effective pre-training.

Description

Groeneveld, Jan; Herrmann, Judith; Mollenhauer, Nikkel; Dreeßen, Leonard; Bessin, Nick; Tast, Johann Schulze; Kastius, Alexander; Huegle, Johannes; Schlosser, Rainer (2024): Self-learning Agents for Recommerce Markets. Business & Information Systems Engineering: Vol. 66, No. 4. DOI: 10.1007/s12599-023-00841-8. Springer. ISSN: 1867-0202

Keywords

Competition, Dynamic pricing, Market simulation, Recommerce, Reinforcement learning, Sustainability

Citation

URI

Endorsement

Review

Supplemented By

Referenced By


Number of citations to item: 7

  • Fabian Lange, Rainer Schlosser (2025): Dynamic pricing with waiting and price-anticipating customers, In: Operations Research Perspectives, doi:10.1016/j.orp.2025.100337
  • David Bendig, Antonio Bräunche (2024): The role of artificial intelligence algorithms in information systems research: a conceptual overview and avenues for research, In: Management Review Quarterly 4(75), doi:10.1007/s11301-024-00451-y
  • Fabian Lange, Rainer Schlosser (2024): Dynamic Pricing with Price-Anticipating Customers, doi:10.2139/ssrn.4992790
  • Fabian Lange, Leonard Dreessen, Rainer Schlosser (2024): Reinforcement Learning vs. Data-Driven Dynamic Programming: A Comparison for Finite Horizon Dynamic Pricing Markets, doi:10.2139/ssrn.4993107
  • Md Monjurul Karim, Sangeen Khan, Dong Hoang Van, Xinyue Liu, Chunhui Wang, Qiang Qu (2025): Transforming Data Annotation with AI Agents: A Review of Architectures, Reasoning, Applications, and Impact, In: Future Internet 8(17), doi:10.3390/fi17080353
  • Fabian Lange, Leonard Dreessen, Rainer Schlosser (2025): Reinforcement learning versus data-driven dynamic programming: a comparison for finite horizon dynamic pricing markets, In: Journal of Revenue and Pricing Management 6(24), doi:10.1057/s41272-025-00519-8
  • Rahul Kumar, Shubhadeep Mukherjee, Divya Choudhary (2025): Uncovering the roots of customer dissatisfaction via Amazon reviews: a hybrid ensemble-deep learning approach for E-commerce quality management, In: Annals of Operations Research 2(353), doi:10.1007/s10479-025-06770-x
Please note: Providing information about citations is only possible thanks to to the open metadata APIs provided by crossref.org and opencitations.net. These lists may be incomplete due to unavailable citation data.source: opencitations.net, crossref.org