Learning Market Parameters Using Aggregate Demand Queries

We study efficient algorithms for a natural learning problem in markets. There is one seller with m divisible goods and n buyers with unknown individual utility functions and budgets of money. The seller can repeatedly announce prices and observe aggregate demand bundles requested by the buyers. The goal of the seller is to learn the utility functions and budgets of the buyers. Our scenario falls into the classic domain of "revealed preference" analysis. Problems with revealed preference have recently started to attract increased interest in computer science due to their fundamental nature in understanding customer behavior in electronic markets. The goal of revealed preference analysis is to observe rational agent behavior, to explain it using a suitable model for the utility functions, and to predict future agent behavior. Our results are the first polynomial-time algorithms to learn utility and budget parameters via revealed preference queries in classic Fisher markets with multiple buyers. Our analysis concentrates on linear, CES, and Leontief markets, which are the most prominent classes studied in the literature. Some of our results extend to general Arrow-Debreu exchange markets.

[1]  K. Arrow,et al.  Capital-labor substitution and economic efficiency , 1961 .

[2]  Richard Cole,et al.  Fast-converging tatonnement algorithms for one-time and ongoing market problems , 2008, STOC.

[3]  H. Varian.  Revealed Preference , 2006 .

[4]  Léon Walras.  Éléments d'économie politique pure, ou, Théorie de la richesse sociale , 1976 .

[5]  Aaron Roth,et al.  Learning from Rational Behavior: Predicting Solutions to Unknown Linear Programs , 2016, NIPS.

[6]  S. Afriat.  THE CONSTRUCTION OF UTILITY FUNCTIONS FROM EXPENDITURE DATA , 1967 .

[7]  P. Samuelson.  Consumption Theory in Terms of Revealed Preference , 1948 .

[8]  A. Mas-Colell,et al.  Microeconomic Theory , 1995 .

[9]  R. Solow.  A Contribution to the Theory of Economic Growth , 1956 .

[10]  Erich Kaltofen.  A Polynomial-Time Reduction from Bivariate to Univariate Integral Polynomial Factorization , 1982, FOCS.

[11]  Morteza Zadimoghaddam,et al.  Efficiently Learning from Revealed Preference , 2012, WINE.

[12]  Olivier de La Grandville,et al.  Economic Growth: A Unified Approach , 2009 .

[13]  László Lovász,et al.  Factoring polynomials with rational coefficients , 1982 .

[14]  Ilya Segal,et al.  Solutions manual for Microeconomic theory : Mas-Colell, Whinston and Green , 1997 .

[15]  Thomas F. Rutherford,et al.  Applied General Equilibrium Modeling with MPSGE as a GAMS Subsystem: An Overview of the Modeling Framework and Syntax , 1999 .

[16]  Maria-Florina Balcan,et al.  Learning Economic Parameters from Revealed Preferences , 2014, WINE.

[17]  Amit Daniely,et al.  Optimal learners for multiclass problems , 2014, COLT.

[18]  Rakesh V. Vohra,et al.  Learning from revealed preference , 2006, EC '06.

[19]  Sriram V. Pemmaraju,et al.  On the polynomial time computation of equilibria for certain exchange economies , 2005, SODA '05.

[20]  Martin Hoefer,et al.  Tatonnement for Linear and Gross Substitutes Markets , 2015, ArXiv.

[21]  Aaron Roth,et al.  Online Learning and Profit Maximization from Revealed Preferences , 2014, AAAI.

[22]  Aaron Roth,et al.  Watch and learn: optimizing from revealed preferences feedback , 2015, SECO.

[23]  Erich Kaltofen,et al.  A polynomial-time reduction from bivariate to univariate integral polynomial factorization , 1982, 23rd Annual Symposium on Foundations of Computer Science (sfcs 1982).

[24]  Yishay Mansour,et al.  Learning What's Going on: Reconstructing Preferences and Priorities from Opaque Transactions , 2015, EC.

[25]  Yishay Mansour,et al.  Learning Valuation Distributions from Partial Observation , 2014, AAAI.

[26]  L. Walras.  Elements of Pure Economics, or The Theory of Social Wealth , 1955 .

[27]  H. Dickinson,et al.  A Note on Dynamic Economics , 1954 .

[28]  Yishay Mansour,et al.  Learning valuation distributions from partial observations , 2015, AAAI 2015.