Enhancing Banking Fraud Detection: Role of Machine Learning and Deep Learning Methods
Bibliographic record
Abstract
Fraud detection in banking is a critical concern as financial institutions face increasing challenges in identifying and preventing fraudulent activities. With the rise of sophisticated fraud schemes, traditional detection methods have proven inadequate, prompting the adoption of machine learning (ML) and deep learning (DL) techniques. This review explores the application of ML and DL methods in banking fraud detection, examining their strengths, limitations, and potential for future improvements. We provide an overview of commonly used ML algorithms such as logistic regression, decision trees, random forests, and support vector machines, as well as advanced DL architectures, including feedforward neural networks (FNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs). In this review, key issues are discussed in data preprocessing, such as handling imbalanced datasets, feature engineering, and ensuring data privacy. Emerging trends in fraud detection, including explainable AI, real-time and edge computing solutions, blockchain integration, and synthetic data generation, are highlighted as promising avenues for enhancing detection systems. Despite the significant progress, challenges such as computational complexity, model interpretability, and adversarial attacks remain. This review concludes by emphasizing the need for continued research and collaboration between academia and industry to develop more effective, transparent, and secure fraud detection systems for the banking sector.
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 | 0.004 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.001 | 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".