Explore the evidence.
Understand the reach.

The utilization of powerful machine learning models in artificial intelligence offers novel prospects for the identification of fraudulent activities. Artificial Intelligence (AI) is a revolutionary technological tool that enhances the ability to detect and prevent fraud by improving efficiency and effectiveness. This research offers a thorough examination of the utilization of artificial intelligence technology in the realm of procurement fraud prevention and detection. Additionally, it highlights the obstacles that arise when employing machine learning techniques for the purpose of identifying and preventing fraudulent activities. A mixed methods approach was employed in this study, wherein data was collected through an unstructured interview and questionnaire. We conducted a comprehensive review of relevant scholarly articles and online resources. The findings indicate that fraudsters are progressively advancing in their skills, which poses a significant challenge in detecting fraudulent activities. The advent of AI in fraud detection has demonstrated its transformative impact. AI has achieved unparalleled precision and velocity in crime detection and prevention, surpassing the capabilities of any human. Artificial intelligence (AI) enhances the capacity for automation. Accessing unstructured data in the form of spreadsheets, digital documents, and email inboxes poses a significant issue for the procurement function. In order to achieve a successful procurement transformation, businesses should prioritize the creation of essential tools, guarantee acceptance through the establishment of a superior user experience, and integrate both novel and pre-existing technology. It is imperative to disseminate knowledge to the general public regarding the escalating sophistication of artificial intelligence (AI) in the realm of fraud detection and prevention. This includes elucidating the potential benefits of AI in identifying patterns of suspicious activities, assessing its efficacy in predicting potential threats or fraudulent activities prior to their manifestation, and exploring its utility in analyzing historical data pertaining to both familiar and unfamiliar forms of fraudulent behavior.

Technological developments play an important role in the audit process, one of which is the use of data analytics that are useful to assist auditors in analyzing data, collecting audit evidence, predicting risks that occur and will occur, and other things. The use of data analytics is also applied by public sector auditors to maintain accountability and responsibility for state finances. This study aims to examine the effect of using data analytics on indications of fraud for public sector examiners in Indonesia. Testing and data analysis techniques used STATA version 14, which processed answers from 33 auditors from two representative offices of public sector auditors in Java Province and Sumatra Province. The results of the study state that the use of data analytics has a positive and significant effect on indications of fraud for public sector examiners in the examination process. This means that public sector auditors can detect fraud using data analytics. Keywords: Audit Process; Public Sector Auditors; Data Analytics; Fraud Detection

The fraudulent claims for Unemployment Insurance (UI) have also risen massively in the United States especially during the onset of COVID-19 pandemic with billions of dollars that were lost. These approaches applied formerly in fraud detection and prevention have been challenged by new and advanced fraud systems. For this reason, AI, Big Data and Predictive Analytics are now crucial for improving fraud mitigation in UI programs. The aim of this research is to understand how far AI, Big Data and Predictive Analytics have been utilized, for how effective they are and the barriers they pose in tackling unemployment insurance fraud in the United States. An online quantitative self-administered questionnaire was administered where 200 participants from the unemployment insurance agencies of the U.S, covering fraud investigators, IT personnel, data analysts and policymakers, were included in the study. Data were analyzed to establish the correlation between technology adoption to application of anti-fraud measures using descriptive statistics, chi-square test and regression analysis. The survey shows that about 42.5% of agencies actively use AI and 34% of them use Big Data very often. However, difficulties like high costs, integration troubles and limited availability of specialized staff are still issues that make adoption a problem. The results of using AI and Big Data were moderate and optimistic but rather elevated, as seen through regression analysis; on the other hand, predictive analytics demonstrated large potential when applied successfully. The study’s results indicate that AI, Big Data and Predictive Analytics present enormous potential for mitigating UI fraud, although broad integration will not be possible without overcoming essential infrastructural and resource limitations.

Using self-reported data from banks in mainland China, I apply a technique used in forensic accounting based on Benford’s Law to detect fraudulent manipulation of non-performing loan (NPL) figures.  I find large data anomalies consistent with false reporting in mainland banks that do not appear in an identically structured survey of Hong Kong banks.  A comparison of different types of data from mainland banks shows no statistically significant anomalies in data for total deposits from customers, operating expenses, net interest income, or non-interest income.

The fraudulent claims for Unemployment Insurance (UI) have also risen massively in the United States especially during the onset of COVID-19 pandemic with billions of dollars that were lost. These approaches applied formerly in fraud detection and prevention have been challenged by new and advanced fraud systems. For this reason, AI, Big Data and Predictive Analytics are now crucial for improving fraud mitigation in UI programs. The aim of this research is to understand how far AI, Big Data and Predictive Analytics have been utilized, for how effective they are and the barriers they pose in tackling unemployment insurance fraud in the United States. An online quantitative self-administered questionnaire was administered where 200 participants from the unemployment insurance agencies of the U.S, covering fraud investigators, IT personnel, data analysts and policymakers, were included in the study. Data were analyzed to establish the correlation between technology adoption to application of anti-fraud measures using descriptive statistics, chi-square test and regression analysis. The survey shows that about 42.5% of agencies actively use AI and 34% of them use Big Data very often. However, difficulties like high costs, integration troubles and limited availability of specialized staff are still issues that make adoption a problem. The results of using AI and Big Data were moderate and optimistic but rather elevated, as seen through regression analysis; on the other hand, predictive analytics demonstrated large potential when applied successfully. The study’s results indicate that AI, Big Data and Predictive Analytics present enormous potential for mitigating UI fraud, although broad integration will not be possible without overcoming essential infrastructural and resource limitations.

The utilization of powerful machine learning models in artificial intelligence offers novel prospects for the identification of fraudulent activities. Artificial Intelligence (AI) is a revolutionary technological tool that enhances the ability to detect and prevent fraud by improving efficiency and effectiveness. This research offers a thorough examination of the utilization of artificial intelligence technology in the realm of procurement fraud prevention and detection. Additionally, it highlights the obstacles that arise when employing machine learning techniques for the purpose of identifying and preventing fraudulent activities. A mixed methods approach was employed in this study, wherein data was collected through an unstructured interview and questionnaire. We conducted a comprehensive review of relevant scholarly articles and online resources. The findings indicate that fraudsters are progressively advancing in their skills, which poses a significant challenge in detecting fraudulent activities. The advent of AI in fraud detection has demonstrated its transformative impact. AI has achieved unparalleled precision and velocity in crime detection and prevention, surpassing the capabilities of any human. Artificial intelligence (AI) enhances the capacity for automation. Accessing unstructured data in the form of spreadsheets, digital documents, and email inboxes poses a significant issue for the procurement function. In order to achieve a successful procurement transformation, businesses should prioritize the creation of essential tools, guarantee acceptance through the establishment of a superior user experience, and integrate both novel and pre-existing technology. It is imperative to disseminate knowledge to the general public regarding the escalating sophistication of artificial intelligence (AI) in the realm of fraud detection and prevention. This includes elucidating the potential benefits of AI in identifying patterns of suspicious activities, assessing its efficacy in predicting potential threats or fraudulent activities prior to their manifestation, and exploring its utility in analyzing historical data pertaining to both familiar and unfamiliar forms of fraudulent behavior.

Technological developments play an important role in the audit process, one of which is the use of data analytics that are useful to assist auditors in analyzing data, collecting audit evidence, predicting risks that occur and will occur, and other things. The use of data analytics is also applied by public sector auditors to maintain accountability and responsibility for state finances. This study aims to examine the effect of using data analytics on indications of fraud for public sector examiners in Indonesia. Testing and data analysis techniques used STATA version 14, which processed answers from 33 auditors from two representative offices of public sector auditors in Java Province and Sumatra Province. The results of the study state that the use of data analytics has a positive and significant effect on indications of fraud for public sector examiners in the examination process. This means that public sector auditors can detect fraud using data analytics. Keywords: Audit Process; Public Sector Auditors; Data Analytics; Fraud Detection

Using self-reported data from banks in mainland China, I apply a technique used in forensic accounting based on Benford’s Law to detect fraudulent manipulation of non-performing loan (NPL) figures.  I find large data anomalies consistent with false reporting in mainland banks that do not appear in an identically structured survey of Hong Kong banks.  A comparison of different types of data from mainland banks shows no statistically significant anomalies in data for total deposits from customers, operating expenses, net interest income, or non-interest income.