Estimating quantities: comparing simple heuristics and machine learning algorithms

  • Authors:

  • Jan K. Woike;Ulrich Hoffrage;Ralph Hertwig

  • Affiliations:

  • Faculty of Business and Economics, University of Lausanne, Switzerland,Faculty of Psychology, University of Basel, Switzerland;Faculty of Business and Economics, University of Lausanne, Switzerland;Faculty of Psychology, University of Basel, Switzerland

  • Venue:
  • ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Estimating quantities is an important everyday task. We analyzed the performance of various estimation strategies in ninety-nine real-world environments drawn from various domains. In an extensive simulation study, we compared two classes of strategies: one included machine learning algorithms such as general regression neural networks and classification and regression trees, the other two psychologically plausible and computationally much simpler heuristics (QEst and Zig-QEst). We report the strategies' ability to generalize from training sets to new data and explore the ecological rationality of their use; that is, how well they perform as a function of the statistical structure of the environment. While the machine learning algorithms outperform the heuristics when fitting data, Zig-QEst is competitive when making predictions out-of-sample.