Integrating Economic Knowledge in Data Mining Algorithms

H.A.M. Daniëls, A.J. Feelders

Research output: Working paperDiscussion paperOther research output

407 Downloads (Pure)

Abstract

The assessment of knowledge derived from databases depends on many factors. Decision makers often need to convince others about the correctness and effectiveness of knowledge induced from data.The current data mining techniques do not contribute much to this process of persuasion.Part of this limitation can be removed by integrating knowledge from experts in the field, encoded in some accessible way, with knowledge derived form patterns stored in the database.In this paper we will in particular discuss methods for implementing monotonicity constraints in economic decision problems.This prior knowledge is combined with data mining algorithms based on decision trees and neural networks.The method is illustrated in a hedonic price model.
Original languageEnglish
Place of PublicationTilburg
PublisherOperations research
Number of pages16
Volume2001-63
Publication statusPublished - 2001

Publication series

NameCentER Discussion Paper
Volume2001-63

Keywords

  • knowledge
  • neural network
  • data mining
  • decision trees

Fingerprint Dive into the research topics of 'Integrating Economic Knowledge in Data Mining Algorithms'. Together they form a unique fingerprint.

  • Cite this

    Daniëls, H. A. M., & Feelders, A. J. (2001). Integrating Economic Knowledge in Data Mining Algorithms. (CentER Discussion Paper; Vol. 2001-63). Operations research.