Presenting the Development of the Beneish Model with Emphasis on Economic Features using Neural Network, Vector Machine, and Random Forest

As the business process becomes more complex, financial statement distortion risk increases. In this regard, researchers have been looking for models to detect fraud in financial statements. Beneish (1997) predicted earning manipulation using financial ratios and accruals. Since economic pressure is...

Full description

Saved in:
Bibliographic Details
Main Authors: Kiumars Pourgadimi, Jamal Bahri Sales, Saeed Jabbarzadeh Kangarloie, Akbar Zavar Rezaee
Format: Article
Language:English
Published: Ferdowsi University of Mashhad 2022-12-01
Series:Iranian Journal of Accounting, Auditing & Finance
Subjects:
Online Access:https://ijaaf.um.ac.ir/article_42173_ab4e5be4eb5f62e7541a247aaa3a5dcd.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846109636464214016
author Kiumars Pourgadimi
Jamal Bahri Sales
Saeed Jabbarzadeh Kangarloie
Akbar Zavar Rezaee
author_facet Kiumars Pourgadimi
Jamal Bahri Sales
Saeed Jabbarzadeh Kangarloie
Akbar Zavar Rezaee
author_sort Kiumars Pourgadimi
collection DOAJ
description As the business process becomes more complex, financial statement distortion risk increases. In this regard, researchers have been looking for models to detect fraud in financial statements. Beneish (1997) predicted earning manipulation using financial ratios and accruals. Since economic pressure is presented as a manager’s external motivation to manipulate income, the Beneish model is developed based on economic variables, including Inflation Rate, GDP Growth, Exchange Rate, and Economic Growth Rate. The fitting of the random forest, vector machine, and neural network was used to fit the extended model. The results show that the accuracy of the random forest model is 99.96% which is more than the neural network and vector models, 96.1% and 93.62%, respectively. The final results show that the developed model is more accurate than the basic Beneish model. The results show that economic factors play a significant role in fraudulent financial reporting which should be considered when analyzing financial reporting.
format Article
id doaj-art-3a1172f5ee6748c1a2b84f0f20e694c3
institution Kabale University
issn 2717-4131
2588-6142
language English
publishDate 2022-12-01
publisher Ferdowsi University of Mashhad
record_format Article
series Iranian Journal of Accounting, Auditing & Finance
spelling doaj-art-3a1172f5ee6748c1a2b84f0f20e694c32024-12-25T06:52:55ZengFerdowsi University of MashhadIranian Journal of Accounting, Auditing & Finance2717-41312588-61422022-12-0164152810.22067/ijaaf.2022.4217342173Presenting the Development of the Beneish Model with Emphasis on Economic Features using Neural Network, Vector Machine, and Random ForestKiumars Pourgadimi0Jamal Bahri Sales1Saeed Jabbarzadeh Kangarloie2Akbar Zavar Rezaee3Department of Accounting, Urmia Branch, Islamic Azad University, Urmia, IranDepartment of Accounting, Urmia Branch, Islamic Azad University, Urmia, IranDepartment of Accounting, Urmia Branch, Islamic Azad University, Urmia, IranDepartment of accounting, Urmia University, Urmia, IranAs the business process becomes more complex, financial statement distortion risk increases. In this regard, researchers have been looking for models to detect fraud in financial statements. Beneish (1997) predicted earning manipulation using financial ratios and accruals. Since economic pressure is presented as a manager’s external motivation to manipulate income, the Beneish model is developed based on economic variables, including Inflation Rate, GDP Growth, Exchange Rate, and Economic Growth Rate. The fitting of the random forest, vector machine, and neural network was used to fit the extended model. The results show that the accuracy of the random forest model is 99.96% which is more than the neural network and vector models, 96.1% and 93.62%, respectively. The final results show that the developed model is more accurate than the basic Beneish model. The results show that economic factors play a significant role in fraudulent financial reporting which should be considered when analyzing financial reporting.https://ijaaf.um.ac.ir/article_42173_ab4e5be4eb5f62e7541a247aaa3a5dcd.pdfbenish modelaudit quality characteristicsneural networkvector machine and random forest
spellingShingle Kiumars Pourgadimi
Jamal Bahri Sales
Saeed Jabbarzadeh Kangarloie
Akbar Zavar Rezaee
Presenting the Development of the Beneish Model with Emphasis on Economic Features using Neural Network, Vector Machine, and Random Forest
Iranian Journal of Accounting, Auditing & Finance
benish model
audit quality characteristics
neural network
vector machine and random forest
title Presenting the Development of the Beneish Model with Emphasis on Economic Features using Neural Network, Vector Machine, and Random Forest
title_full Presenting the Development of the Beneish Model with Emphasis on Economic Features using Neural Network, Vector Machine, and Random Forest
title_fullStr Presenting the Development of the Beneish Model with Emphasis on Economic Features using Neural Network, Vector Machine, and Random Forest
title_full_unstemmed Presenting the Development of the Beneish Model with Emphasis on Economic Features using Neural Network, Vector Machine, and Random Forest
title_short Presenting the Development of the Beneish Model with Emphasis on Economic Features using Neural Network, Vector Machine, and Random Forest
title_sort presenting the development of the beneish model with emphasis on economic features using neural network vector machine and random forest
topic benish model
audit quality characteristics
neural network
vector machine and random forest
url https://ijaaf.um.ac.ir/article_42173_ab4e5be4eb5f62e7541a247aaa3a5dcd.pdf
work_keys_str_mv AT kiumarspourgadimi presentingthedevelopmentofthebeneishmodelwithemphasisoneconomicfeaturesusingneuralnetworkvectormachineandrandomforest
AT jamalbahrisales presentingthedevelopmentofthebeneishmodelwithemphasisoneconomicfeaturesusingneuralnetworkvectormachineandrandomforest
AT saeedjabbarzadehkangarloie presentingthedevelopmentofthebeneishmodelwithemphasisoneconomicfeaturesusingneuralnetworkvectormachineandrandomforest
AT akbarzavarrezaee presentingthedevelopmentofthebeneishmodelwithemphasisoneconomicfeaturesusingneuralnetworkvectormachineandrandomforest