An Approach To Generate Rules From Neural Networks for Regression Problems

European Journal of Operational Research, 155, 1 (2004), pp. 239-250.

HKUST Business School Research Paper No. 2021-005

16 Pages Posted: 23 Mar 2021 Last revised: 4 Jun 2021

See all articles by Rudy Setiono

Rudy Setiono

National University of Singapore

James Y.L. Thong

HKUST Business School

Date Written: 2004

Abstract

Artificial neural networks have been successfully applied to a variety of business application problems involving classification and regression. They are especially useful for regression problems as they do not require prior knowledge about the data distribution. In many applications, it is desirable to extract knowledge from trained neural networks so that the users can gain a better understanding of the solution. Existing research works have focused primarily on extracting symbolic rules for classification problems with few methods devised for regression problems. In order to fill this gap, we propose an approach to extract rules from neural networks that have been trained to solve regression problems. The extracted rules divide the data samples into groups. For all samples within a group, a linear function of the relevant input attributes of the data approximates the network output. The approach is illustrated with two examples on various application problems. Experimental results show that the proposed approach generates rules that are more accurate than the existing methods based on decision trees and linear regression.

Keywords: Neural Networks, Nonlinear Regression, Curve Fitting, Machine Learning, Knowledge-Based Systems

JEL Classification: C45, M15

Suggested Citation

Setiono, Rudy and Thong, James Y.L., An Approach To Generate Rules From Neural Networks for Regression Problems (2004). European Journal of Operational Research, 155, 1 (2004), pp. 239-250., HKUST Business School Research Paper No. 2021-005, Available at SSRN: https://ssrn.com/abstract=3766019

Rudy Setiono

National University of Singapore ( email )

Singapore

James Y.L. Thong (Contact Author)

HKUST Business School ( email )

Clear Water Bay
Kowloon
Hong Kong

HOME PAGE: http://jthong.people.ust.hk/

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
28
Abstract Views
327
PlumX Metrics