Competition between firms using dynamic pricing algorithms

Cover Page

Cite item

Full Text

Abstract

the development of modern data collection and analysis technologies is leading to increasing automation of pricing in commodity markets. More and more firms are using pricing algorithms, the consequences of which remain unclear. Most studies consider such algorithms when the firm is a monopolist. The current paper compares several dynamic pricing algorithms in a competitive environment. It is assumed that two firms use algorithms independently and are unaware of the other's algorithm choice. Several algorithms are compared through a series of algorithm duels: two simple algorithms based on the multi-armed bandit problem, a parametric algorithm based on weighted linear regression learning, and a Q-learning algorithm. The results show that the use of different algorithms can lead to price dispersion. Also, algorithm complexity does not always equate to greater firm profits. The work also shows that if firms chose pricing algorithms non-cooperatively in an algorithm choice game, then two Nash equilibria could emerge in the market: a symmetric equilibrium, where both firms choose complex Q-learning algorithms and earn low profits, and an asymmetric equilibrium, where firms choose different algorithms, earn high profits, but one firm is the leader.

About the authors

P. S Pronin

Plekhanov Russian University of Economics

References

  1. Alamdar P., Seifi A. deep Q-learning approach to optimize ordering and dynamic pricing decisions in the presence of strategic customers // International Journal of Production Economics. 2024. № 269. P. 109 – 154.
  2. Berry S., Levinsohn J., Pakes A.Automobile prices in market equilibrium // Econometrica. 1995. № 63 (4). P. 841 – 890.
  3. Burman V., Vashishtha R.K., Kumar R., Ramanan S. Deep reinforcement learning for dynamic pricing of perishable products // International Conference on Optimization and Learning. Cham: Springer International Publishing, 2021. P. 132 – 143.
  4. Calvano E., Calzolari G., Denicolo V., Pastorello S. Artificial intelligence, algorithmic pricing, and collusion // American Economic Review. 2020. № 110 (10). P. 3267 – 3297.
  5. Cavallo A. More Amazon effects: online competition and pricing behaviors // National Bureau of Economic Research. 2018. № 25138. P. 1 – 37.
  6. Den Boer A.V. Dynamic pricing and learning: Historical origins, current research, and new directions // Surveys in operations research and management science. 2015. № 20 (1). P. 1 – 8.
  7. Den Boer A.V., Keskin N.B. Dynamic pricing and demand learning in nonstationary environments // The Elements of Joint Learning and Optimization in Operations Management. Cham: Springer International Publishing, 2022. P. 137 – 150.
  8. Den Boer A.V., Zwart B. Simultaneously learning and optimizing using controlled variance pricing // Management science. 2014. № 60 (3). P. 770 – 783.
  9. Deng S., Schiffer M., Bichler M.Algorithmic collusion in dynamic pricing with deep reinforcement learning // arXiv preprint. 2024. № 2406.02437. P. 1 – 20.
  10. Elreedy D.A. F. Atiya, S. I. Shaheen Novel pricing strategies for revenue maximization and demand learning using an exploration–exploitation framework // Soft Computing. 2021. № 25 (17). P. 11711 – 11733.
  11. Huang Y.P.B., Ellickson M.J. Lovett Learning to set prices // Journal of Marketing Research. 2022. № 59 (2). P. 411 – 434.
  12. Kastius A.R. Schlosser Dynamic pricing under competition using reinforcement learning // Journal of Revenue and Pricing Management. 2021. № 21 (1). P. 50 – 63.
  13. Klein T. Autonomous algorithmic collusion: Q?learning under sequential pricing // The RAND Journal of Economics. 2021. № 52 (3). P. 538 – 558.
  14. Kleinberg R.T. Leighton The value of knowing a demand curve: Bounds on regret for online posted-price auctions // 44th Annual IEEE Symposium on Foundations of Computer Science. 2003. P. 594 – 605.
  15. Luo Y.W.W. Sun Y. Liu Distribution-free contextual dynamic pricing // Mathematics of Operations Research. 2024. № 49 (1). P. 599 – 618.
  16. Meylahn J.M., Den A.V. Boer Learning to collude in a pricing duopoly // Manufacturing & Service Operations Management. 2022. № 24 (5). P. 2577 – 2594.
  17. Misra K.E.M., Schwartz J. Abernethy Dynamic online pricing with incomplete information using multiarmed bandit experiments // Marketing Science. 2019. № 38 (2). P. 226 – 252.
  18. Slivkins A. Introduction to multi-armed bandits // Foundations and Trends® in Machine Learning. 2019. № 12. P. 1 – 286.
  19. Sutton R.S., Barto A.G. Reinforcement Learning: An Introduction. 2 изд. Cambridge: MIT Press, 2018. 552 p.
  20. Trovo F., Paladino S., Restelli M., Gatti N. Multi-armed bandit for pricing // Proceedings of the 12th European Workshop on Reinforcement Learnin. 2015. P. 1 – 9.

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Согласие на обработку персональных данных

 

Используя сайт https://journals.rcsi.science, я (далее – «Пользователь» или «Субъект персональных данных») даю согласие на обработку персональных данных на этом сайте (текст Согласия) и на обработку персональных данных с помощью сервиса «Яндекс.Метрика» (текст Согласия).