A Systematic Review of Machine Learning Advances in Financial Fraud Detection for Banking Systems
Bibliographic record
Abstract
Financial fraud in banking systems constitutes one of the most consequential operational risks confronting global financial institutions, with annual losses estimated across fraud typologies including payment card fraud, account takeover, synthetic identity fraud, and money laundering. This systematic review synthesises literature on machine learning advances in financial fraud detection published between 2010 and 2022, examining 312 peer-reviewed studies across supervised, unsupervised, and hybrid detection architectures. The review maps methodological evolution from logistic regression baselines through ensemble gradient boosting methods, deep learning architectures, graph neural networks, and federated learning frameworks. XGBoost and gradient-boosted ensemble methods consistently achieve AUC-ROC values above 0.97 under optimally calibrated sampling strategies. Four primary deployment challenges are identified and examined: class imbalance management, concept drift in evolving fraud patterns, regulatory interpretability requirements, and real-time scoring latency. A Responsible Analytics Framework integrating technical excellence, regulatory compliance by design, continuous monitoring, human oversight, and equity assurance is proposed with supporting comparative tables.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.023 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.011 | 0.006 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.007 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".