A potential use of data envelopment analysis for the inverse classification problem

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

We propose a methodology that uses data envelopment analysis (DEA) for solving the inverse classification problem. An inverse classification problem involves finding out how predictor attributes of a case can be changed so that the case can be classified into a different and more desirable class. For a binary classification problem and non-negative decision-making attributes, we show that under the assumption of conditional monotonicity, and convexity of classes, DEA can be used for inverse classification problem. We illustrate the application of our proposed methodology on a hypothetical and a real-life bankruptcy prediction data.

Original languageEnglish (US)
Pages (from-to)243-248
Number of pages6
JournalOmega
Volume30
Issue number3
DOIs
StatePublished - Jun 17 2002

Fingerprint

Data envelopment analysis
Methodology
Convexity
Bankruptcy prediction
Predictors
Monotonicity
Decision making

All Science Journal Classification (ASJC) codes

  • Strategy and Management
  • Information Systems and Management
  • Management Science and Operations Research

Cite this

@article{bb347b4c909242be8d354a760eff3aca,
title = "A potential use of data envelopment analysis for the inverse classification problem",
abstract = "We propose a methodology that uses data envelopment analysis (DEA) for solving the inverse classification problem. An inverse classification problem involves finding out how predictor attributes of a case can be changed so that the case can be classified into a different and more desirable class. For a binary classification problem and non-negative decision-making attributes, we show that under the assumption of conditional monotonicity, and convexity of classes, DEA can be used for inverse classification problem. We illustrate the application of our proposed methodology on a hypothetical and a real-life bankruptcy prediction data.",
author = "Pendharkar, {Parag C.}",
year = "2002",
month = "6",
day = "17",
doi = "10.1016/S0305-0483(02)00030-0",
language = "English (US)",
volume = "30",
pages = "243--248",
journal = "Omega",
issn = "0305-0483",
publisher = "Elsevier BV",
number = "3",

}

A potential use of data envelopment analysis for the inverse classification problem. / Pendharkar, Parag C.

In: Omega, Vol. 30, No. 3, 17.06.2002, p. 243-248.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A potential use of data envelopment analysis for the inverse classification problem

AU - Pendharkar, Parag C.

PY - 2002/6/17

Y1 - 2002/6/17

N2 - We propose a methodology that uses data envelopment analysis (DEA) for solving the inverse classification problem. An inverse classification problem involves finding out how predictor attributes of a case can be changed so that the case can be classified into a different and more desirable class. For a binary classification problem and non-negative decision-making attributes, we show that under the assumption of conditional monotonicity, and convexity of classes, DEA can be used for inverse classification problem. We illustrate the application of our proposed methodology on a hypothetical and a real-life bankruptcy prediction data.

AB - We propose a methodology that uses data envelopment analysis (DEA) for solving the inverse classification problem. An inverse classification problem involves finding out how predictor attributes of a case can be changed so that the case can be classified into a different and more desirable class. For a binary classification problem and non-negative decision-making attributes, we show that under the assumption of conditional monotonicity, and convexity of classes, DEA can be used for inverse classification problem. We illustrate the application of our proposed methodology on a hypothetical and a real-life bankruptcy prediction data.

UR - http://www.scopus.com/inward/record.url?scp=0036271668&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036271668&partnerID=8YFLogxK

U2 - 10.1016/S0305-0483(02)00030-0

DO - 10.1016/S0305-0483(02)00030-0

M3 - Article

AN - SCOPUS:0036271668

VL - 30

SP - 243

EP - 248

JO - Omega

JF - Omega

SN - 0305-0483

IS - 3

ER -