No-regret Learning in Price Competitions under Consumer Reference Effects

We study long-run market stability for repeated price competitions between two firms, where consumer demand depends on firms' posted prices and consumers' price expectations called reference prices. Consumers' reference prices vary over time according to a memory-based dynamic, which is a weighted average of all historical prices. We focus on the setting where firms are not aware of demand functions and how reference prices are formed but have access to an oracle that provides a measure of consumers' responsiveness to the current posted prices. We show that if the firms run no-regret algorithms, in particular, online mirror descent(OMD), with decreasing step sizes, the market stabilizes in the sense that firms' prices and reference prices converge to a stable Nash Equilibrium (SNE). Interestingly, we also show that there exist constant step sizesunder which the market stabilizes. We further characterize the rate of convergence to the SNE for both decreasing and constant OMD step sizes.

[1]  Steven C. H. Hoi,et al.  Online Learning: A Comprehensive Survey , 2018, Neurocomputing.

[2]  G. Kalyanaram,et al.  Empirical Generalizations from Reference Price Research , 1995 .

[3]  N. B. Keskin,et al.  Dynamic Pricing with Demand Learning and Reference Effects , 2020, Manag. Sci..

[4]  Paul R. Milgrom,et al.  Rationalizability, Learning, and Equilibrium in Games with Strategic Complementarities , 1990 .

[5]  Awi Federgruen,et al.  Price Competition Based on Relative Prices , 2016 .

[6]  Georgia Perakis,et al.  Dynamic Pricing and Inventory Control: Uncertainty and Competition , 2010, Oper. Res..

[7]  Lakshman Krishnamurthi,et al.  A comparative analysis of reference price models , 1997 .

[8]  A. Tversky,et al.  Prospect Theory : An Analysis of Decision under Risk Author ( s ) : , 2007 .

[9]  Yuri Levin,et al.  Dynamic Pricing in the Presence of Strategic Consumers and Oligopolistic Competition , 2009, Manag. Sci..

[10]  David S. Leslie,et al.  Bandit learning in concave $N$-person games , 2018, 1810.01925.

[11]  Srini Krishnamoorthy,et al.  Pricing strategies with reference effects in competitive industries , 2014, Int. Trans. Oper. Res..

[12]  A. Tversky,et al.  Advances in prospect theory: Cumulative representation of uncertainty , 1992 .

[13]  Hyun-Soo Ahn,et al.  Pricing and Manufacturing Decisions When Demand is a Function of Prices in Multiple Periods , 2007, Oper. Res..

[14]  Federico Echenique,et al.  A short and constructive proof of Tarski’s fixed-point theorem , 2005, Int. J. Game Theory.

[15]  Asuman E. Ozdaglar,et al.  Distributed Subgradient Methods for Multi-Agent Optimization , 2009, IEEE Transactions on Automatic Control.

[16]  A. Tversky,et al.  Prospect theory: an analysis of decision under risk — Source link , 2007 .

[17]  Gadi Fibich,et al.  Explicit Solutions of Optimization Models and Differential Games with Nonsmooth (Asymmetric) Reference-Price Effects , 2003, Oper. Res..

[18]  Sébastien Bubeck,et al.  Introduction to Online Optimization , 2011 .

[19]  Jian Huang,et al.  Demand Functions in Decision Modeling: A Comprehensive Survey and Research Directions , 2013, Decis. Sci..

[20]  Russell S. Winer,et al.  A reference price model of brand choice for frequently purchased products. , 1986 .

[21]  Julian Zimmert,et al.  Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits , 2018, J. Mach. Learn. Res..

[22]  Mathias Staudigl,et al.  Convergence to nash equilibrium in continuous games with noisy first-order feedback , 2017, 2017 IEEE 56th Annual Conference on Decision and Control (CDC).

[23]  Yonatan Gur,et al.  Learning in Repeated Auctions with Budgets: Regret Minimization and Equilibrium , 2017, EC.

[24]  Hugo Hopenhayn Entry, exit, and firm dynamics in long run equilibrium , 1992 .

[25]  Ramesh Johari,et al.  Equilibria of Dynamic Games with Many Players: Existence, Approximation, and Market Structure , 2010, J. Econ. Theory.

[26]  Marc Teboulle,et al.  Convergence Analysis of a Proximal-Like Minimization Algorithm Using Bregman Functions , 1993, SIAM J. Optim..

[27]  P. Kopalle,et al.  Asymmetric Reference Price Effects and Dynamic Pricing Policies , 1996 .

[28]  E. Greenleaf The Impact of Reference Price Effects on the Profitability of Price Promotions , 1995 .

[29]  Fernando Bernstein,et al.  A General Equilibrium Model for Industries with Price and Service Competition , 2004, Oper. Res..

[30]  M. Satterthwaite,et al.  Computable Markov-Perfect Industry Dynamics: Existence, Purification, and Multiplicity , 2007 .

[31]  Holger Boche,et al.  Pricing Mechanism for Resource Sustainability in Competitive Online Learning Multi-Agent Systems , 2019, ArXiv.

[32]  Robert Phillips,et al.  Price Competition with the Attraction Demand Model: Existence of Unique Equilibrium and Its Stability , 2006, Manuf. Serv. Oper. Manag..

[33]  Ioana Popescu,et al.  Dynamic Pricing Strategies with Reference Effects , 2007, Oper. Res..

[34]  Awi Federgruen,et al.  Price Competition Under Mixed Multinomial Logit Demand Functions , 2013, Manag. Sci..

[35]  Ioana Popescu,et al.  Dynamic Pricing with Loss Averse Consumers and Peak-End Anchoring , 2010, Oper. Res..

[36]  Juan F. Escobar Existence of Pure and Behavior Strategy Stationary Markov Equilibrium in Dynamic Stochastic Games , 2007 .

[37]  Francisco Facchinei,et al.  Convex Optimization, Game Theory, and Variational Inequality Theory , 2010, IEEE Signal Processing Magazine.

[38]  Julian Zimmert,et al.  Beating Stochastic and Adversarial Semi-bandits Optimally and Simultaneously , 2019, ICML.

[39]  Yurii Nesterov,et al.  Introductory Lectures on Convex Optimization - A Basic Course , 2014, Applied Optimization.

[40]  A. Nagurney,et al.  Projected Dynamical Systems and Variational Inequalities with Applications , 1995 .

[41]  Ming Hu,et al.  Dynamic Pricing of Perishable Assets under Competition , 2013, Manag. Sci..

[42]  M. Porter,et al.  Market Structure, Oligopoly, and Stability of Market Shares , 1978 .

[43]  PopescuIoana,et al.  Dynamic Pricing Strategies with Reference Effects , 2007 .

[44]  Xin Chen,et al.  Technical Note - Dynamic Pricing with Gain-Seeking Reference Price Effects , 2016, Oper. Res..

[45]  Zhengyuan Zhou,et al.  Learning in games with continuous action sets and unknown payoff functions , 2019, Math. Program..