Learning economic parameters from revealed preferences

DOI10.1007/978-3-319-13129-0_28MaRDI QIDQ2936997zbMATH OpenOpenAlexFDO

Authors Maria-Florina Balcan, Amit Daniely, Ruta Mehta, Ruth Urner, Vijay V. Vazirani

Publication date 7 January 2015

Published in Web and Internet Economics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1407.7937

zbMATH Keywords

efficient algorithmslinearquery learningrevealed preferenceSPLC and Leontief utility functionsstatistical learning

Mathematics Subject Classification ID

Software, source code, etc. for problems pertaining to game theory, economics, and finance (91-04) Rationality and learning in game theory (91A26) Individual preferences (91B08) Utility theory (91B16)

Abstract: A recent line of work, starting with Beigman and Vohra (2006) and Zadimoghaddam and Roth (2012), has addressed the problem of {em learning} a utility function from revealed preference data. The goal here is to make use of past data describing the purchases of a utility maximizing agent when faced with certain prices and budget constraints in order to produce a hypothesis function that can accurately forecast the {em future} behavior of the agent. In this work we advance this line of work by providing sample complexity guarantees and efficient algorithms for a number of important classes. By drawing a connection to recent advances in multi-class learning, we provide a computationally efficient algorithm with tight sample complexity guarantees ($Theta(d/epsilon)$ for the case of $d$ goods) for learning linear utility functions under a linear price model. This solves an open question in Zadimoghaddam and Roth (2012). Our technique yields numerous generalizations including the ability to learn other well-studied classes of utility functions, to deal with a misspecified model, and with non-linear prices.

Recommendations

• Kernel methods for revealed preference analysis
• Social welfare and profit maximization from revealed preferences
• Revealed preference theory: an algorithmic outlook
• Recover dynamic utility from observable process: application to the economic equilibrium
• Learning in nonlinear pricing with unknown utility functions

Cited in

(7)

• Social welfare and profit maximization from revealed preferences
• Achieving target equilibria in network routing games without knowing the latency functions
• Kernel methods for revealed preference analysis
• Learning time dependent choice
• On the limitations of data-based price discrimination
• Agnostic learning with unknown utilities
• Learning a decision maker's utility function from (possibly) inconsistent behavior

This page was built for publication: Learning economic parameters from revealed preferences

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2936997)