Financial Frauds
Author: Nutan Rasal.
MMS – Roll No: 0222047
Kohinoor Business School
Literature review
Financial Fraud Identification Based On Stacking Ensemble Learning Algorithm: Introducing MD&A Text Information.
Zhang, Z., Ma, Y., & Hua, Y. (2022) et al. “Financial Fraud Identification Based on Stacking Ensemble Learning Algorithm: Introducing MD&A Text Information” discusses a model for identifying financial fraud using the stacking ensemble learning algorithm. The model incorporates the text of the management discussion and analysis (MD&A) chapter in annual reports, using sentiment polarity, emotional tone, and text readability as text variables. The model is expected to provide a new and more effective method for identifying financial fraud by taking financial, non-financial, and text indicators as sample features. The authors declare that there are no conflicts of interest regarding the publication of this paper.
Identification And Early Warning Of Financial Fraud Risk Based On Bidirectional Long-Short Term Memory Model.
Liu, X., & Fan, M. (2022) et al. “The article proposes a method for identifying and providing early warning of financial fraud risk based on a bidirectional long-short-term memory model. The model is designed to predict the probability of missed payments and credit card fraud using LSTM algorithms. The proposed model is expected to help financial institutions detect and prevent fraudulent activities by analyzing customer behavior and identifying potential risks. The article highlights the importance of using advanced machine-learning techniques to improve fraud detection and prevention in the financial industry.
Using GNN To Detect Financial Fraud Based On The Related Party Transactions Network.
Mao, X., Liu, M., & Wang, Y. (2022) et al. “The article discusses the use of Graph Neural Networks (GNN) to detect financial fraud based on the related party transactions network. The authors note that related party transactions increase the risk of financial fraud, and propose using GNN to identify fraudulent transactions. GNN is a type of machine learning algorithm that can analyze complex networks and identify patterns. The article suggests that GNN can be used to classify transactions as fraudulent or non-fraudulent based on their network connections. The authors believe that this approach can improve fraud detection in financial systems. The article was published in the academic journal Procedia Computer Science in 2021.
PE‐EDD: An Efficient Peer‐Effect‐Based Financial Fraud Detection Approach In Publicly Traded China Firms.
Hui Xia, Hui Ma, & Ping Cheng. (2022) et al. “The article titled “PE-EDD: An efficient peer-effect-based financial fraud detection approach in publicly traded China Firms” proposes a new method for detecting financial fraud in publicly traded Chinese companies. The method is based on the idea that fraudulent behavior can be detected by analyzing the behavior of peer companies in the same industry. The authors use raw financial data and ensemble learning algorithms to detect fraudulent behavior. The study provides direct evidence for rapid fraud detection using financial report raw data and ensemble learning algorithms. The proposed method has the potential to be an effective tool for detecting financial fraud in publicly traded Chinese companies.
Estimating Financial Fraud Through Transaction-Level Features And Machine Learning.
Alwadain, A., Ali, R. F., & Muneer, A. (2023) et al. “The article “Estimating Financial Fraud through Transaction-Level Features and Machine Learning” discusses the use of machine learning techniques to detect financial fraud. Fraud detection is usually framed as a classification problem, where the goal is to predict a discrete class label output given a set of data. Fraudulent transactions have specific features that can be identified using machine-learning algorithms. The article shows that machine-learning techniques can be applied successfully to detect fraudulent transactions. By using machine learning in fraud detection, financial institutions can identify fake accounts, suspicious transactions, and payment fraud.
Corporate Social Responsibility, Financial Fraud, And Firm’s Value In Indonesia And Malaysia
Tarjo Tarjo, Alexander Anggono, Rita Yuliana, Prasetyono Prasetyono, Muh Syarif, Muhammad Alkirom Wildan, & Muhammad Syam Kusufi. (2022) et al. “The article examines the relationship between corporate social responsibility (CSR), financial fraud, and firm value in Indonesia and Malaysia. The study uses a fixed effect model based on the Houseman diagnostic test statistics and proxies of CSR, including Global Reporting Initiative, religiosity, philanthropy, voluntary environmental disclosure index, and ISO 26000. The proxy of financial fraud is the F-Score model. The research reveals that financial fraud can reduce the impact of CSR on a firm’s value. The study focuses on mining companies engaged in Indonesia and Malaysia’s oil and gas sectors. The main finding of the study is that financial fraud can weaken the influence of CSR on firm value. Financial fraud in the company harmed the stakeholders, so the company’s value decreased.
Cryptocurrencies As A Subject Of Financial Fraud.
Kutera, M. (2022) et al. “According to a new analysis from the Federal Trade Commission, consumers reported losing over $1 billion to fraud involving cryptocurrencies from January 2021 through March 2022. Cryptocurrency fraud has become a growing concern worldwide, with a 190% increase in losses for victims of scams involving cryptocurrencies between 2017 and 2018. Cryptocurrency is quickly becoming the payment of choice for many scammers, with about one out of every four dollars reported lost to fraud paid in cryptocurrency. Most of the cryptocurrency losses consumers reported involved bogus cryptocurrency investment opportunities, which totaled $575 million in reported losses since January 2021. These scams often falsely promise potential investors that they can earn huge returns by investing in their cryptocurrency schemes, but people report losing all the money they “invest.
Detecting Financial Fraud Using Two Types Of Benford Factors: Evidence From China.
Gong, Y., Li, J., Xu, Z., & Li, G. (2022) et al. “The article “Detecting Financial Fraud using Two Types of Benford Factors: Evidence from China. Discusses how financial fraud of listed companies can lead to anomalies in the distribution of financial data, which can be detected by Benford’s Law. The study takes financial data of Chinese listed companies to construct two types of Benford factors for detecting financial fraud. Benford’s Law is a tool for fraud detection that can be used to identify accounting fraud and data manipulation in corporate firms. It is expected that the data related to fraudulent companies will not comply with Benford’s law, as fraud makes changes in the numbers of financial statements.
Can Fraud In Islamic Financial Institutions Be Prevented Using High Standards Of Shariah Governance?
Swandaru, R., & Muneeza, A. (2022) et al. “According to the search results, there is evidence to suggest that high standards of Shariah governance can help prevent fraud in Islamic financial institutions. Several studies have emphasized the importance of Shariah governance frameworks in preventing fraud and increasing profitability in Islamic finance. One study aims to scrutinize the modus operandi of global financial frauds in Islamic financial institutions and assess whether those frauds can be prevented using high standards of Shariah governance. Overall, the evidence suggests that implementing high standards of Shariah governance can help prevent fraud in Islamic financial institutions.
ATOVIS – A Visualization Tool For The Detection Of Financial Fraud.
Maçãs, C., Polisciuc, E., & Machado, P. (2022) et al. “ATOVIS is a visualization tool developed to aid in the detection of financial fraud. It provides an overview of specific patterns within the data and enables details on demand, which can help ease and accelerate fraud detection. The tool is designed to detect and stop fraudulent transactions, which encompasses the automatic detection of fraudulent cases through a machine-learning algorithm and the manual detection of fraud through human analysis of low-confidence transactions. ATOVIS is primarily specialized in Account Takeover (ATO) patterns and is considered an efficient and effective tool for detecting specific patterns of fraud, which can improve the analysts’ work.
Conclusion:
The provided search results discuss various machine-learning techniques used for financial fraud detection. Machine learning algorithms such as logistic regression, decision trees, random forests, and unsupervised learning techniques can be used to detect financial fraud. These algorithms are trained with historical data to identify patterns and anomalies that may indicate fraudulent activity. In machine learning, fraud detection is usually framed as a classification problem, where the algorithm predicts a discrete class label output given data input. By using these techniques, financial institutions can identify and prevent fraudulent activities, which can help protect their customers and their business.
REFERENCE
Zhang, Z., Ma, Y., & Hua, Y. (2022). Financial Fraud Identification Based on Stacking Ensemble Learning Algorithm: Introducing MD&A Text Information. Computational Intelligence & Neuroscience, 2022, 1–14. https://doi.org/10.1155/2022/1780834
Liu, X., & Fan, M. (2022). Identification and Early Warning of Financial Fraud Risk Based on Bidirectional Long-Short Term Memory Model. Mathematical Problems in Engineering, 1–8. https://doi.org/10.1155/2022/2342312
Mao, X., Liu, M., & Wang, Y. (2022). Using GNN to detect financial fraud based on the related party transactions network. Procedia Computer Science, 214, 351–358. https://doi.org/10.1016/j.procs.2022.11.185
Hui Xia, Hui Ma, & Ping Cheng. (2022). PE‐EDD: An efficient peer‐effect‐based financial fraud detection approach in publicly traded China firms. CAAI Transactions on Intelligence Technology, 7(3), 469–480. https://doi.org/10.1049/cit2.12057
Alwadain, A., Ali, R. F., & Muneer, A. (2023). Estimating Financial Fraud through Transaction-Level Features and Machine Learning. Mathematics (2227-7390), 11(5), 118
4. https://doi.org/10.3390/math11051184
Tarjo Tarjo, Alexander Anggono, Rita Yuliana, Prasetyono Prasetyono, Muh Syarif, Muhammad Alkirom Wildan, & Muhammad Syam Kusufi. (2022). Corporate social responsibility, financial fraud, and firm’s value in Indonesia and Malaysia. Heliyon, 8(12). https://doi.org/10.1016/j.heliyon.2022.e11907
Kutera, M. (2022). Cryptocurrencies as a subject of financial fraud. Journal of Entrepreneurship, Management & Innovation, 18(4), 45–77. https://doi.org/10.7341/20221842
Gong, Y., Li, J., Xu, Z., & Li, G. (2022). Detecting Financial Fraud using Two Types of Benford Factors: Evidence from China. Procedia Computer Science, 214, 656–663. https://doi.org/10.1016/j.procs.2022.11.225
Swandaru, R., & Muneeza, A. (2022). Can fraud in Islamic financial institutions be prevented using high standards of Shariah governance? International Journal of Law & Management, 64(6), 469–485. https://doi.org/10.1108/IJLMA-07-2022-0162
Maçãs, C., Polisciuc, E., & Machado, P. (2022). ATOVIS – A visualization tool for the detection of financial fraud. Information Visualization, 21(4), 371–392. https://doi.org/10.1177/14738716221098074