Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0366
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-07-20T09:09:44.648425Z
status: published
lens: g_space
sector: crime
headline: Financial fraud detection through the application of machine learning techniques: a literature review
dek: Financial fraud negatively impacts organizational administrative processes, particularly affecting owners and/or investors seeking to maximize their profits. Addressing this issue, this study presents a literature review on financial fraud detection through machine learning techniques. The PRISMA and Kitchenham methods were applied, and 104 articles published between 2012 and 2023 were examined. These articles were selected based on predefined inclusion and exclusion criteria and were obtained from databases suc…
gain_title: Literature shows machine learning models are applied to detect financial fraud, with credit card fraud detection models most widely used.
problem_title: (none)
trace_subject: (none)
gain_reading: Literature shows machine learning models are applied to detect financial fraud, with credit card fraud detection models most widely used.
gain_evidence: credit card fraud detection models are the most widely used for detecting credit card loan fraud | Machine learning models and metrics were used to assess performance
problem_reading: (none)
problem_evidence: (none)
quick_read: Published September 3, 2024, this peer-reviewed literature review applied PRISMA and Kitchenham methods to 104 articles from 2012-2023 obtained from Scopus, IEEE Xplore, Taylor & Francis, SAGE, and ScienceDirect to map how machine learning is used to detect financial fraud and its types.

The synthesis matters because it shows where detection research concentrates and where gaps remain: credit card fraud models dominate, real datasets are favored while synthetic data accounts for less than 7%, and contributions cluster in China, India, Saudi Arabia, and Canada with few publications from Latin America, leaving questions about generalizability across regions and fraud types.
limitation: Review coverage is geographically skewed and relies heavily on real datasets with limited synthetic data testing.
tag: Evidence-backed gain
key_points: PRISMA and Kitchenham methods applied to 104 articles published between 2012 and 2023 from Scopus, IEEE Xplore, Taylor & Francis, SAGE, and ScienceDirect. | Analysis indicated a trend toward using real datasets, with synthetic data use below 7% of employed datasets. | Data sources included stock exchanges of China, Canada, United States, Taiwan, and Tehran, with leading contributors from China, India, Saudi Arabia, and Canada.
rundown: The review examined 104 articles from 2012 to 2023 selected via predefined inclusion and exclusion criteria, extracting information on authors, sources, countries, trends, and datasets used in experiments.

Findings highlight that credit card fraud detection models dominate the literature, real datasets are increasingly preferred over synthetic, and data were sourced from exchanges in China, Canada, the United States, Taiwan, and Tehran among others.
sources:
- peer_reviewed | Humanities and Social Sciences Communications | https://doi.org/10.1057/s41599-024-03606-0 | 2024-09-03
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

5e3554276c9e02f68903f3d0400072d099f0fa15372e52eb26c9df8c635e3b5a

previous

0000000000000000000000000000000000000000000000000000000000000000