Learning Economic Parameters from Revealed Preferences

  • Maria-Florina Balcan
  • Amit Daniely
  • Ruta Mehta
  • Ruth Urner
  • Vijay V. Vazirani
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8877)


A recent line of work, starting with Beigman and Vohra [4] and Zadimoghaddam and Roth [30], has addressed the problem of 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 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 (\(\tilde{\Theta}(d/\epsilon)\) 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 [30]. 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.


revealed preference statistical learning query learning efficient algorithms Linear SPLC and Leontief utility functions 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Afriat, S.N.: The construction of utility functions from expenditure data. International Economic Review (1967)Google Scholar
  2. 2.
    Balcan, M.F., Daniely, A., Mehta, R., Urner, R., Vazirani, V.V.: Learning economic parameters from revealed preferences (2014),
  3. 3.
    Bazarra, M.S., Sherali, H.D., Shetty, C.M.: Nonlinear Programming: Theory and Algorithms. John Wiley & Sons (2006)Google Scholar
  4. 4.
    Beigman, E., Vohra, R.: Learning from revealed preference. In: EC, pp. 36–42 (2006)Google Scholar
  5. 5.
    Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press (2009)Google Scholar
  6. 6.
    Collins, M.: Discriminative reranking for natural language parsing. In: ICML, pp. 175–182 (2000)Google Scholar
  7. 7.
    Collins, M.: Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms. In: Proceedings of the ACL 2002 Conference on Empirical Methods in Natural Language Processing, EMNLP 2002, vol. 10, pp. 1–8. Association for Computational Linguistics, Stroudsburg (2002)CrossRefGoogle Scholar
  8. 8.
    Crammer, K., Singer, Y.: On the algorithmic implementation of multiclass kernel-based vector machines. Journal of Machine Learning Research 2, 265–292 (2001)Google Scholar
  9. 9.
    Daniely, A., Shalev-Shwartz, S.: Optimal learners for multiclass problems. In: COLT, pp. 287–316 (2014)Google Scholar
  10. 10.
    Diewert, E.: Afriat and revealed preference theory. Review of Economic Studies 40, 419–426 (1973)CrossRefzbMATHGoogle Scholar
  11. 11.
    Dobell, A.R.: A comment on A. Y. C. Koo’s an empirical test of revealed preference theory. Econometrica 33(2), 451–455 (1965)CrossRefGoogle Scholar
  12. 12.
    Echenique, F., Golovin, D., Wierman, A.: A revealed preference approach to computational complexity in economics. In: EC, pp. 101–110 (2011)Google Scholar
  13. 13.
    Haussler, D., Welzl, E.: Epsilon-nets and simplex range queries. In: Symposium on Computational Geometry, pp. 61–71 (1986)Google Scholar
  14. 14.
    Houthakker, H.S.: Revealed preference and the utility function. Economica 17, 159–174 (1950)CrossRefMathSciNetGoogle Scholar
  15. 15.
    Koo, A.Y.C.: An empirical test of revealed preference theory. Econometrica 31(4), 646–664 (1963)CrossRefMathSciNetGoogle Scholar
  16. 16.
    Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: ICML, pp. 282–289 (2001)Google Scholar
  17. 17.
    Lahaie, S.: Kernel methods for revealed preference analysis. In: European Conference on Artificial Intelligence, pp. 439–444 (2010)Google Scholar
  18. 18.
    Littlestone, N., Warmuth, M.K.: Relating data compression and learnability. Unpulished manuscript (1986)Google Scholar
  19. 19.
    Mas-Colell, A.: The recoverability of consumers’ preferences from market demand. Econometrica 45(6), 1409–1430 (1977)CrossRefzbMATHGoogle Scholar
  20. 20.
    Mas-Colell, A.: On revealed preference analysis. The Review of Economic Studies 45(1), 121–131 (1978)CrossRefzbMATHMathSciNetGoogle Scholar
  21. 21.
    Mas-Colell, A., Whinston, M.D., Green, J.R.: Microeconomic Theory. Oxford University Press, New York (1995)zbMATHGoogle Scholar
  22. 22.
    Natarajan, B.: On learning sets and functions. Machine Learning 4(1), 67–97 (1989)Google Scholar
  23. 23.
    Richter, M.: Revealed preference theory. Econometrica 34(3), 635–645 (1966)CrossRefzbMATHGoogle Scholar
  24. 24.
    Samuelson, P.: Consumption theory in terms of revealed preference. Econometrica 15 (1948)Google Scholar
  25. 25.
    Shalev-Shwartz, S., Ben-David, S.: Understanding Machine Learning. Cambridge University Press (2014)Google Scholar
  26. 26.
    Uzawa, H.: Preference and rational choice in the theory of consumption. In: Arrow, K.J., Karlin, S., Suppes, P. (eds.) Mathematical Models in Social Science (1960)Google Scholar
  27. 27.
    Valiant, L.G.: A theory of the learnable. Commun. ACM 27(11), 1134–1142 (1984)CrossRefzbMATHGoogle Scholar
  28. 28.
    Varian, H.R.: The non-parametric approach to demand analysis. Econometrica 50, 945–974 (1982)CrossRefzbMATHMathSciNetGoogle Scholar
  29. 29.
    Varian, H.R.: Revealed preference. In: Szenberg, M., Ramrattand, L., Gottesman, A.A. (eds.) Samuelsonian Economics and the 21st Century, pp. 99–115 (2005)Google Scholar
  30. 30.
    Zadimoghaddam, M., Roth, A.: Efficiently learning from revealed preference. In: Goldberg, P.W. (ed.) WINE 2012. LNCS, vol. 7695, pp. 114–127. Springer, Heidelberg (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Maria-Florina Balcan
    • 1
  • Amit Daniely
    • 2
  • Ruta Mehta
    • 3
  • Ruth Urner
    • 1
  • Vijay V. Vazirani
    • 3
  1. 1.Department of Machine LearningCarnegie Mellon UniversityUSA
  2. 2.Department of MathematicsThe Hebrew UniversityIsrael
  3. 3.School of Computer ScienceGeorgia Institute of TechnologyUSA

Personalised recommendations