The theory is predictive, but is it complete? an application to human perception of randomness

Jon Kleinberg, Annie Liang, Sendhil Mullainathan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Scopus citations

Abstract

When we test theories, it is common to focus on what one might call predictiveness: how well do the theory's predictions match what we see in data? Evidence that a theory is predictive, however, provides little guidance towards whether there may exist alternative theories that are more predictive, and how much more predictive they might be. These questions point toward a second issue, distinct from predictiveness, which we call completeness: how close is the performance of a given theory to the best performance that is achievable in the domain? Completeness is an important construct because it lets us ask how much room there is for improving the predictive performance of existing theories in any given domain. We would expect the best possible prediction performance to di.er considerably across domains-for example, an accuracy of 55% is a stunning success for predicting stock movements based on past returns, but extremely weak for predicting movements of a planet based on physical measurements. .is contrast rejects that variation in stock movements conditioned on the features we know is large, while planetary motions are well predicted by known features. To understand how much we can improve on the predictive performance of existing theories, we need to separate prediction error due to intrinsic noise (emerging from limitations of the feature set) from prediction error that reveals opportunities for a be.er model.

Original languageEnglish (US)
Title of host publicationEC 2017 - Proceedings of the 2017 ACM Conference on Economics and Computation
PublisherAssociation for Computing Machinery, Inc
Pages125-126
Number of pages2
ISBN (Electronic)9781450345279
DOIs
StatePublished - Jun 20 2017
Externally publishedYes
Event18th ACM Conference on Economics and Computation, EC 2017 - Cambridge, United States
Duration: Jun 26 2017Jun 30 2017

Publication series

NameEC 2017 - Proceedings of the 2017 ACM Conference on Economics and Computation

Other

Other18th ACM Conference on Economics and Computation, EC 2017
Country/TerritoryUnited States
CityCambridge
Period6/26/176/30/17

Keywords

  • Prediction
  • Randomness perception
  • Theory completeness

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Statistics and Probability
  • Computational Mathematics
  • Economics and Econometrics

Fingerprint

Dive into the research topics of 'The theory is predictive, but is it complete? an application to human perception of randomness'. Together they form a unique fingerprint.

Cite this