Financial fraud detection through the application of machine learning techniques: a literature review
Bibliographic record
Abstract
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 such as Scopus, IEEE Xplore, Taylor & Francis, SAGE, and ScienceDirect. These selected articles, along with the contributions of authors, sources, countries, trends, and datasets used in the experiments, were used to detect financial fraud and its existing types. Machine learning models and metrics were used to assess performance. The analysis indicated a trend toward using real datasets. Notably, credit card fraud detection models are the most widely used for detecting credit card loan fraud. The information obtained by different authors was acquired from the stock exchanges of China, Canada, the United States, Taiwan, and Tehran, among other countries. Furthermore, the usage of synthetic data has been low (less than 7% of the employed datasets). Among the leading contributors to the studies, China, India, Saudi Arabia, and Canada remain prominent, whereas Latin American countries have few related publications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.010 | 0.010 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".