Using decision tree induction systems for modeling space-time behavior

T.A. Arentze, F. Hofman, H. Mourik, van, H.J.P. Timmermans, G. Wets

Research output: Contribution to journalArticleAcademicpeer-review

29 Citations (Scopus)

Abstract

Discrete choice models are commonly used to predict individuals' activity and travel choices either separately or simultaneously in activity scheduling models. This paper investigates the possibilities of decision tree induction systems as an alternative approach. The ability of decision frees to represent heuristic decision rules is evaluated and a method of capturing interactions across decisions In a sequential decision model is outlined. Decision tree induction algorithms, such as C4.5, CART, and CHAID, are suited to device the decision rules from empirical data. A case study to illustrate the approach considers decisions of individuals when they are faced with the choice to combine different out-of-home activities into a multipurpose, multistop trip or make a trip fbr each activity separately. Data fron a large-scale activity diary survey are used to induce the decision rules. Possible directions of future research are identified.
Original languageEnglish
Pages (from-to)330-350
JournalGeographical Analysis
Volume32
Issue number4
DOIs
Publication statusPublished - 2000

Fingerprint

Dive into the research topics of 'Using decision tree induction systems for modeling space-time behavior'. Together they form a unique fingerprint.

Cite this