Financial statement fraud detection in indonesia listed companies using machine learning based on meta-heuristic optimization

Syafiq Hidayattullah; Isti Surjandari; Enrico Laoh

doi:10.1109/IWBIS50925.2020.9255563

Financial statement fraud detection in indonesia listed companies using machine learning based on meta-heuristic optimization

Syafiq Hidayattullah, Isti Surjandari, Enrico Laoh

Department of Industrial Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Citations (Scopus)

Abstract

Financial statement is a critical document which form the basis of decisions of various stakeholders in the capital market. Ironically, the phenomenon of fraud on the company's financial statements is not a practice that never happened. Data reported by ACFE in 2020 showed that financial statement fraud is the costliest category of occupational fraud with median loss of 954.000. This study utilizes several machine learning approaches based on meta-heuristic optimization to develop robust fraud prediction models in financial statements. Two classification methods were used, namely, Back Propagation Neural Networks and Support Vector Machines. The best classifier in this study is a Support Vector Machine, which parameters are optimized with Genetic Algorithm resulting in 96.15% accuracy.

Original language	English
Title of host publication	2020 International Workshop on Big Data and Information Security, IWBIS 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	79-84
Number of pages	6
ISBN (Electronic)	9781728190983
DOIs	https://doi.org/10.1109/IWBIS50925.2020.9255563
Publication status	Published - 17 Oct 2020
Event	5th International Workshop on Big Data and Information Security, IWBIS 2020 - Depok, Indonesia Duration: 17 Oct 2020 → 18 Oct 2020

Publication series

Name	2020 International Workshop on Big Data and Information Security, IWBIS 2020

Conference

Conference	5th International Workshop on Big Data and Information Security, IWBIS 2020
Country/Territory	Indonesia
City	Depok
Period	17/10/20 → 18/10/20

Keywords

Classification
Financial Statement Fraud
Fraud Detection
Genetic Algorithm
Machine Learning

Access to Document

10.1109/IWBIS50925.2020.9255563

Cite this

Hidayattullah, S., Surjandari, I., & Laoh, E. (2020). Financial statement fraud detection in indonesia listed companies using machine learning based on meta-heuristic optimization. In 2020 International Workshop on Big Data and Information Security, IWBIS 2020 (pp. 79-84). Article 9255563 (2020 International Workshop on Big Data and Information Security, IWBIS 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IWBIS50925.2020.9255563

Hidayattullah, Syafiq ; Surjandari, Isti ; Laoh, Enrico. / Financial statement fraud detection in indonesia listed companies using machine learning based on meta-heuristic optimization. 2020 International Workshop on Big Data and Information Security, IWBIS 2020. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 79-84 (2020 International Workshop on Big Data and Information Security, IWBIS 2020).

@inproceedings{58aa446e57ea4f2a922f6e2249774e37,

title = "Financial statement fraud detection in indonesia listed companies using machine learning based on meta-heuristic optimization",

abstract = "Financial statement is a critical document which form the basis of decisions of various stakeholders in the capital market. Ironically, the phenomenon of fraud on the company's financial statements is not a practice that never happened. Data reported by ACFE in 2020 showed that financial statement fraud is the costliest category of occupational fraud with median loss of 954.000. This study utilizes several machine learning approaches based on meta-heuristic optimization to develop robust fraud prediction models in financial statements. Two classification methods were used, namely, Back Propagation Neural Networks and Support Vector Machines. The best classifier in this study is a Support Vector Machine, which parameters are optimized with Genetic Algorithm resulting in 96.15% accuracy. ",

keywords = "Classification, Financial Statement Fraud, Fraud Detection, Genetic Algorithm, Machine Learning",

author = "Syafiq Hidayattullah and Isti Surjandari and Enrico Laoh",

note = "Funding Information: ACKNOWLEDGEMENT Authors would like to express gratitude and appreciation to Universitas Indonesia for funding this study through PUTI Prosiding Research Grants Universitas Indonesia No: NKB-0061/UN2.R3.1/HKP .05.00/2020. Publisher Copyright: {\textcopyright} 2020 IEEE.; 5th International Workshop on Big Data and Information Security, IWBIS 2020 ; Conference date: 17-10-2020 Through 18-10-2020",

year = "2020",

month = oct,

day = "17",

doi = "10.1109/IWBIS50925.2020.9255563",

language = "English",

series = "2020 International Workshop on Big Data and Information Security, IWBIS 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "79--84",

booktitle = "2020 International Workshop on Big Data and Information Security, IWBIS 2020",

address = "United States",

}

Hidayattullah, S, Surjandari, I & Laoh, E 2020, Financial statement fraud detection in indonesia listed companies using machine learning based on meta-heuristic optimization. in 2020 International Workshop on Big Data and Information Security, IWBIS 2020., 9255563, 2020 International Workshop on Big Data and Information Security, IWBIS 2020, Institute of Electrical and Electronics Engineers Inc., pp. 79-84, 5th International Workshop on Big Data and Information Security, IWBIS 2020, Depok, Indonesia, 17/10/20. https://doi.org/10.1109/IWBIS50925.2020.9255563

Financial statement fraud detection in indonesia listed companies using machine learning based on meta-heuristic optimization. / Hidayattullah, Syafiq; Surjandari, Isti; Laoh, Enrico.
2020 International Workshop on Big Data and Information Security, IWBIS 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 79-84 9255563 (2020 International Workshop on Big Data and Information Security, IWBIS 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Financial statement fraud detection in indonesia listed companies using machine learning based on meta-heuristic optimization

AU - Hidayattullah, Syafiq

AU - Surjandari, Isti

AU - Laoh, Enrico

N1 - Funding Information: ACKNOWLEDGEMENT Authors would like to express gratitude and appreciation to Universitas Indonesia for funding this study through PUTI Prosiding Research Grants Universitas Indonesia No: NKB-0061/UN2.R3.1/HKP .05.00/2020. Publisher Copyright: © 2020 IEEE.

PY - 2020/10/17

Y1 - 2020/10/17

N2 - Financial statement is a critical document which form the basis of decisions of various stakeholders in the capital market. Ironically, the phenomenon of fraud on the company's financial statements is not a practice that never happened. Data reported by ACFE in 2020 showed that financial statement fraud is the costliest category of occupational fraud with median loss of 954.000. This study utilizes several machine learning approaches based on meta-heuristic optimization to develop robust fraud prediction models in financial statements. Two classification methods were used, namely, Back Propagation Neural Networks and Support Vector Machines. The best classifier in this study is a Support Vector Machine, which parameters are optimized with Genetic Algorithm resulting in 96.15% accuracy.

AB - Financial statement is a critical document which form the basis of decisions of various stakeholders in the capital market. Ironically, the phenomenon of fraud on the company's financial statements is not a practice that never happened. Data reported by ACFE in 2020 showed that financial statement fraud is the costliest category of occupational fraud with median loss of 954.000. This study utilizes several machine learning approaches based on meta-heuristic optimization to develop robust fraud prediction models in financial statements. Two classification methods were used, namely, Back Propagation Neural Networks and Support Vector Machines. The best classifier in this study is a Support Vector Machine, which parameters are optimized with Genetic Algorithm resulting in 96.15% accuracy.

KW - Classification

KW - Financial Statement Fraud

KW - Fraud Detection

KW - Genetic Algorithm

KW - Machine Learning

UR - http://www.scopus.com/inward/record.url?scp=85097597955&partnerID=8YFLogxK

U2 - 10.1109/IWBIS50925.2020.9255563

DO - 10.1109/IWBIS50925.2020.9255563

M3 - Conference contribution

AN - SCOPUS:85097597955

T3 - 2020 International Workshop on Big Data and Information Security, IWBIS 2020

SP - 79

EP - 84

BT - 2020 International Workshop on Big Data and Information Security, IWBIS 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th International Workshop on Big Data and Information Security, IWBIS 2020

Y2 - 17 October 2020 through 18 October 2020

ER -

Hidayattullah S, Surjandari I, Laoh E. Financial statement fraud detection in indonesia listed companies using machine learning based on meta-heuristic optimization. In 2020 International Workshop on Big Data and Information Security, IWBIS 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 79-84. 9255563. (2020 International Workshop on Big Data and Information Security, IWBIS 2020). doi: 10.1109/IWBIS50925.2020.9255563

Financial statement fraud detection in indonesia listed companies using machine learning based on meta-heuristic optimization

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this