NEW LP BASED HEURISTICS FOR THE CLASSIFICATION PROBLEM

被引：29

作者：

ABAD, PL

BANKS, WJ

机构：

[1] WILFRID LAURIER UNIV, SCH BUSINESS & ECON, WATERLOO N2L 3C5, ONTARIO, CANADA

[2] MCMASTER UNIV, FAC BUSINESS, HAMILTON L8S 4M4, ON, CANADA

来源：

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH | 1993年 / 67卷 / 01期

基金：

加拿大自然科学与工程研究理事会;

关键词：

LINEAR PROGRAMMING; DISCRIMINANT ANALYSIS; LINEAR STATISTICAL MODELS; STATISTICAL TECHNIQUES;

D O I：

10.1016/0377-2217(93)90324-G

中图分类号：

C93 [管理学];

学科分类号：

12 ; 1201 ; 1202 ; 120202 ;

摘要：

Three heuristic procedures for the two group discriminant problem are developed that minimize the total expected cost of misclassification in the training sample. The approach is shown through a systematic experiment to generate near optimal solutions and to be efficient in terms of computational effort when compared to existing research.

引用

页码：88 / 100

页数：13

共 23 条

[1]

Bajgier S. M., 1982, Decision Sciences, V13, P604, DOI 10.1111/j.1540-5915.1982.tb01185.x

[2] AN EFFICIENT OPTIMAL SOLUTION ALGORITHM FOR THE CLASSIFICATION PROBLEM [J].