A Comprehensive Review of Machine Learning Techniques in Fraud Detection
Bibliographic record
Abstract
In the era of technology, most of the peoples are dependent on the latest technology in the form of payments. In the financial sector, the growing number of credit card users presents several important implications, which is leading the users away from the cash payments, the significant increase of credit card use resulted in a decrease in reliance on cash advances. Due to rise in credit card, the financial sector is facing several risks despite having Improved Security and Fraud Detection, Advanced Technology: The adoption of EMV chips, contactless payments, and AI-driven fraud detection systems has enhanced transaction security. These technologies help to protect consumers and merchants from fraud. Detecting financial fraud is complicated by class imbalance, which requires the use of rare data mining approaches along with traditional classification algorithms. To address this, we propose conducting an experimental study to assess the impact of class imbalance and measure the resulting conflict in the imbalanced data. For which we have discussed a variety of papers. These publications, which were collected from sources like Scopus and IEEE Xplore, were chosen using predetermined criteria. These chosen publications were utilized to identify fraud (credit card, UPI, identity theft, fraud loans etc.), with the help of various machine learning methods (KNN, CR7, Gradient boost etc.), the authors' contributions, nations, trends, sources, and datasets used in the tests. The data/reports gathered by different authors used to detect frauds, obtained from the stock exchange and banks of India, China, Canada, the United States etc. One of the foremost contributors of the studies, India, the United States, China, Saudi Arabia remain influential, whereas other countries have a limited number of 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 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.007 | 0.011 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.003 |
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".