Home
Resource
Cluster analysis for anomaly detection in accounting
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(1.81 MB)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Thiprungsri, Sutapat. Cluster analysis for anomaly detection in accounting. Retrieved from https://doi.org/doi:10.7282/T35T3JHD

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleCluster analysis for anomaly detection in accounting
NameThiprungsri, Sutapat (author); Vasarhelyi, Miklos (chair); Kogan, Alexander (internal member); Alles, Michael (internal member); Ye, Jianming (outside member); Rutgers University; Graduate School - Newark
Date Created2012
Other Date2012-01 (degree)
SubjectManagement, Cluster analysis, Auditing—Statistical methods
Extentxi, 167 p. : ill.
DescriptionCluster Analysis is a useful technique for grouping data points such that points within a single group or cluster are similar, while points in different groups are different. The objective of this study is to examine the possibility of using clustering technology for auditing. Automating fraud filtering can be of great value to continuous audits. In the first paper, cluster analysis is used to group transactions from a transitory account of a large international bank. Transactions are clustered based on the open comments field. Major types of transactions are discovered. These results provide a new knowledge about the nature of transactions that flow into transitory accounts. In the second paper, cluster analysis is applied to wire payments within an insurance company. Different anomaly detection techniques are examined. No wire transfer is flagged by all techniques. These results do not necessarily indicate that there is no real anomaly in the dataset, but that different assumptions, parameters or settings should be examined. In the third paper, cluster analysis is applied to group life insurance claims. Individual claims which have significantly different characteristic from other members in the same cluster as well as clusters which comprise of less than 2% of the population are identified as possible anomalies. Moreover, rule-based detection techniques are used to assist internal auditors in selecting claims for further investigation. Cluster analysis and rule-based detection can be combined for the efficiency and effectiveness of the implementation by internal auditors. Cluster analysis has been used extensively in marketing as a way to understand market segments and customer behavior. This study examines the application of cluster analysis in the accounting domain. It can be used for exploratory data analysis (EDA), but also can be used for anomaly detection (i.e. for audit purposes). The results provide a guideline and evidence for the potential application of this technique in the field of audit.
NotePh.D.
NoteIncludes bibliographical references
NoteIncludes vita
Noteby Sutapat Thiprungsri
Genretheses, ETD doctoral
Persistent URLhttps://doi.org/doi:10.7282/T35T3JHD
Languageeng
CollectionGraduate School - Newark Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024