Unsupervised Learning Applications in Financial Fraud Detection See Significant Growth

A recent analysis of publications related to unsupervised learning applications in financial fraud detection has revealed a significant increase in research output over the past five years. According to data from 27 identified sources, the number of publications in this field has grown steadily since 2015.

History of Research Output

The study, which examined the intersection of machine learning and financial fraud, found that the first publication in this domain emerged in 2010 with only one article. However, there was a notable decline between 2014 and 2017, with no publications matching the specified criteria during that period. The classification subsequently reappeared in 2018, followed by a resurgence in recent years.

Leading Journals

The analysis also found that two journals - “Risks” and “Advances In Science Technology And Engineering Systems” - have emerged as leading platforms for scholarly contributions in this field. These journals have published four articles each, reflecting their significance in the research domain.

• “Risks”: Focuses on financial fraud risks within the insurance industry
• “Advances In Science Technology And Engineering Systems”: Showcases a wide-ranging scope of interest spanning finance and engineering

Comprehensive Reference Analysis

A comprehensive reference analysis revealed that 28 publications have received more than 10 citations, with the study conducted by Thiprungsri and Vasarhelyi (2011) emerging as the most cited work. This study’s focus on the critical intersection of machine learning and financial fraud detection reflects the significance of this research domain in garnering scholarly attention.

Conclusion

This study provides valuable insights into the growth and development of unsupervised learning applications in financial fraud detection. The findings highlight the importance of “Risks” and “Advances In Science Technology And Engineering Systems” as leading platforms for scholarly contributions in this field, while also underscoring the enduring interest and relevance of research exploring the connection between machine learning and financial fraud.