Using a genetic algorithm-based classifier system for modeling auditor decision behavior in a fraud setting

Abstract

This paper addresses a classification problem involving the decisions of Defense Contractor Audit Agency (DCAA) auditors when they are estimating the likelihood of fraud by contractors developing bids for government contracts. The objective of the study is to investigate if this decision involves non‐algebraic processes associated with a posited simultaneous decision model or algebraic processes posited by sequential decision processes. We propose that in classification decision models involving simultaneous processing, genetic algorithms represent an innovative heuristic approach, which may produce improved models when compared to traditional mathematical approaches. © 1998 John Wiley & Sons, Ltd.

Auditing models for the detection of qualified audit opinions in the UK public services sector

“…Spathis (2003) reports in-sample (i.e., training) overall classification accuracies equal to 75% and 78%, similar to Ruiz- Barbadillo et al (2004) that report in-sample overall classification accuracy equal to79.7%. The results are also similar in studies that used re-sampling techniques such as Spathis et al (2002Spathis et al ( , 2003, or holdout samples such as Welch et al (1998) to test the models and report overall classification accuracies between 71.79% and 86.91%.…”

Auditing models for the detection of qualified audit opinions in the UK public services sector

“…Spathis (2003) reports in-sample (i.e., training) overall classification accuracies equal to 75% and 78%, similar to Ruiz- Barbadillo et al (2004) that report in-sample overall classification accuracy equal to79.7%. The results are also similar in studies that used re-sampling techniques such as Spathis et al (2002Spathis et al ( , 2003, or holdout samples such as Welch et al (1998) to test the models and report overall classification accuracies between 71.79% and 86.91%.…”

External Auditors’ Decisions in EU Credit Institutions: A Multicriteria Approach

“…The results are not significantly different in studies that used re‐sampling techniques such as Spathis et al . (2002, 2003) or holdout samples such as Welch et al . (1998) and Pasiouras et al .…”

AI-Audit: The Perspectives of Digital Technology Application in the Audit Activity

“…In the research O.J. Welch describes the algorithms and patterns of auditor's behavior when detecting fraud risks [Welch, 1998]. For the going-concern assessment of the audited organization activity M. J. Lenard et al develop genetic software.…”

Auditing models for the detection of qualified audit opinions in the UK public services sector

“…Spathis (2003) reports in-sample (i.e., training) overall classification accuracies equal to 75% and 78%, similar to Ruiz- Barbadillo et al (2004) that report in-sample overall classification accuracy equal to79.7%. The results are also similar in studies that used re-sampling techniques such as Spathis et al (2002Spathis et al ( , 2003, or holdout samples such as Welch et al (1998) to test the models and report overall classification accuracies between 71.79% and 86.91%.…”

External Auditors’ Decisions in EU Credit Institutions: A Multicriteria Approach

“…The results are not significantly different in studies that used re‐sampling techniques such as Spathis et al . (2002, 2003) or holdout samples such as Welch et al . (1998) and Pasiouras et al .…”

AI-Audit: The Perspectives of Digital Technology Application in the Audit Activity

“…In the research O.J. Welch describes the algorithms and patterns of auditor's behavior when detecting fraud risks [Welch, 1998]. For the going-concern assessment of the audited organization activity M. J. Lenard et al develop genetic software.…”

Auditing models for the detection of qualified audit opinions in the UK public services sector

“…Spathis (2003) reports in-sample (i.e., training) overall classification accuracies equal to 75% and 78%, similar to Ruiz- Barbadillo et al (2004) that report in-sample overall classification accuracy equal to79.7%. The results are also similar in studies that used re-sampling techniques such as Spathis et al (2002Spathis et al ( , 2003, or holdout samples such as Welch et al (1998) to test the models and report overall classification accuracies between 71.79% and 86.91%.…”

External Auditors’ Decisions in EU Credit Institutions: A Multicriteria Approach

“…The results are not significantly different in studies that used re‐sampling techniques such as Spathis et al . (2002, 2003) or holdout samples such as Welch et al . (1998) and Pasiouras et al .…”

AI-Audit: The Perspectives of Digital Technology Application in the Audit Activity

“…In the research O.J. Welch describes the algorithms and patterns of auditor's behavior when detecting fraud risks [Welch, 1998]. For the going-concern assessment of the audited organization activity M. J. Lenard et al develop genetic software.…”