Preventing and Identifying Fraudulent Activities in Accounting through the Application of Data Science Techniques
Vasim Ahmad, Richa Goel, M. M. L. Arora, Anita Venaik, Rakesh Kumar
Abstract
Fraudulent activities can cause significant financial losses for businesses, and accounting departments are particularly vulnerable to such activities. The use of data science techniques has emerged as a powerful tool in detecting and preventing fraud in accounting. Study explores the application of data science techniques for fraud detection in accounting, including data mining, machine learning, and statistical analysis. It goes over how these methods can be used to spot financial data trends and anomalies that might point to fraud. Additionally, it examines the potential benefits of implementing data science techniques in fraud prevention, such as reducing false positives and improving the accuracy of fraud detection. Evolving Fraud Techniques, Imbalanced Data, and Overlapping Anomalies are the few challenges that are faced over the years. Overall, this study emphasizes the importance of utilizing data science techniques to prevent and identify fraudulent activities in accounting, as it can lead to significant cost savings and protect the integrity of financial data.