Predicting similarity judgments in intertemporal choice with machine learning

Research output: Contribution to journalArticle

Abstract

Similarity models of intertemporal choice are heuristics that choose based on similarity judgments of the reward amounts and time delays. Yet, we do not know how these judgments are made. Here, we use machine-learning algorithms to assess what factors predict similarity judgments and whether decision trees capture the judgment outcomes and process. We find that combining small and large values into numerical differences and ratios and arranging them in tree-like structures can predict both similarity judgments and response times. Our results suggest that we can use machine learning to not only model decision outcomes but also model how decisions are made. Revealing how people make these important judgments may be useful in developing interventions to help them make better decisions.

Original languageEnglish (US)
Pages (from-to)627-635
Number of pages9
JournalPsychonomic Bulletin and Review
Volume25
Issue number2
DOIs
StatePublished - Apr 1 2018

Fingerprint

Decision Trees
Reward
Reaction Time
Machine Learning
Similarity Judgments
Intertemporal Choice
Decision Tree
Response Time
Heuristics

Keywords

  • Classification tree
  • Decision tree
  • Intertemporal choice
  • Judgment
  • Machine learning
  • Similarity

ASJC Scopus subject areas

  • Experimental and Cognitive Psychology
  • Developmental and Educational Psychology
  • Arts and Humanities (miscellaneous)

Cite this

Predicting similarity judgments in intertemporal choice with machine learning. / Stevens, Jeffrey R; Soh, Leen-Kiat.

In: Psychonomic Bulletin and Review, Vol. 25, No. 2, 01.04.2018, p. 627-635.

Research output: Contribution to journalArticle

@article{0e294bf325bc48fca22b8d96acac0fa1,
title = "Predicting similarity judgments in intertemporal choice with machine learning",
abstract = "Similarity models of intertemporal choice are heuristics that choose based on similarity judgments of the reward amounts and time delays. Yet, we do not know how these judgments are made. Here, we use machine-learning algorithms to assess what factors predict similarity judgments and whether decision trees capture the judgment outcomes and process. We find that combining small and large values into numerical differences and ratios and arranging them in tree-like structures can predict both similarity judgments and response times. Our results suggest that we can use machine learning to not only model decision outcomes but also model how decisions are made. Revealing how people make these important judgments may be useful in developing interventions to help them make better decisions.",
keywords = "Classification tree, Decision tree, Intertemporal choice, Judgment, Machine learning, Similarity",
author = "Stevens, {Jeffrey R} and Leen-Kiat Soh",
year = "2018",
month = "4",
day = "1",
doi = "10.3758/s13423-017-1398-1",
language = "English (US)",
volume = "25",
pages = "627--635",
journal = "Psychonomic Bulletin and Review",
issn = "1069-9384",
publisher = "Springer New York",
number = "2",

}

TY - JOUR

T1 - Predicting similarity judgments in intertemporal choice with machine learning

AU - Stevens, Jeffrey R

AU - Soh, Leen-Kiat

PY - 2018/4/1

Y1 - 2018/4/1

N2 - Similarity models of intertemporal choice are heuristics that choose based on similarity judgments of the reward amounts and time delays. Yet, we do not know how these judgments are made. Here, we use machine-learning algorithms to assess what factors predict similarity judgments and whether decision trees capture the judgment outcomes and process. We find that combining small and large values into numerical differences and ratios and arranging them in tree-like structures can predict both similarity judgments and response times. Our results suggest that we can use machine learning to not only model decision outcomes but also model how decisions are made. Revealing how people make these important judgments may be useful in developing interventions to help them make better decisions.

AB - Similarity models of intertemporal choice are heuristics that choose based on similarity judgments of the reward amounts and time delays. Yet, we do not know how these judgments are made. Here, we use machine-learning algorithms to assess what factors predict similarity judgments and whether decision trees capture the judgment outcomes and process. We find that combining small and large values into numerical differences and ratios and arranging them in tree-like structures can predict both similarity judgments and response times. Our results suggest that we can use machine learning to not only model decision outcomes but also model how decisions are made. Revealing how people make these important judgments may be useful in developing interventions to help them make better decisions.

KW - Classification tree

KW - Decision tree

KW - Intertemporal choice

KW - Judgment

KW - Machine learning

KW - Similarity

UR - http://www.scopus.com/inward/record.url?scp=85033359935&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85033359935&partnerID=8YFLogxK

U2 - 10.3758/s13423-017-1398-1

DO - 10.3758/s13423-017-1398-1

M3 - Article

C2 - 29119404

AN - SCOPUS:85033359935

VL - 25

SP - 627

EP - 635

JO - Psychonomic Bulletin and Review

JF - Psychonomic Bulletin and Review

SN - 1069-9384

IS - 2

ER -