Change search
ReferencesLink to record
Permanent link

Direct link
Locally Induced Predictive Models
University of Borås, School of Business and IT. (CSL@BS)
University of Borås, School of Business and IT. (CSL@BS)
University of Borås, School of Business and IT. (CSL@BS)
2011 (English)Conference paper (Refereed)
Abstract [en]

Most predictive modeling techniques utilize all available data to build global models. This is despite the wellknown fact that for many problems, the targeted relationship varies greatly over the input space, thus suggesting that localized models may improve predictive performance. In this paper, we suggest and evaluate a technique inducing one predictive model for each test instance, using only neighboring instances. In the experimentation, several different variations of the suggested algorithm producing localized decision trees and neural network models are evaluated on 30 UCI data sets. The main result is that the suggested approach generally yields better predictive performance than global models built using all available training data. As a matter of fact, all techniques producing J48 trees obtained significantly higher accuracy and AUC, compared to the global J48 model. For RBF network models, with their inherent ability to use localized information, the suggested approach was only successful with regard to accuracy, while global RBF models had a better ranking ability, as seen by their generally higher AUCs.

Place, publisher, year, edition, pages
IEEE , 2011.
Keyword [en]
local learning, predictive modeling, decision trees, rbf networks, Machine Learning
Keyword [sv]
Data Mining
National Category
Computer Science Computer and Information Science
Research subject
Bussiness and IT
URN: urn:nbn:se:hb:diva-6767DOI: 10.1109/ICSMC.2011.6083922Local ID: 2320/10327ISBN: 978-1-4577-0651-6OAI: diva2:887469
IEEE International Conference on Systems, Man, and Cybernetics
Available from: 2015-12-22 Created: 2015-12-22

Open Access in DiVA

fulltext(327 kB)5 downloads
File information
File name FULLTEXT01.pdfFile size 327 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Search in DiVA

By author/editor
Johansson, UlfLöfström, TuveSönströd, Cecilia
By organisation
School of Business and IT
Computer ScienceComputer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 5 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 14 hits
ReferencesLink to record
Permanent link

Direct link