Machine Learning Algorithms for Financial Fraud Detection
Clicks: 47
ID: 309124
2022
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This
article has not been analysed, so there is no overall score —
reader engagement is measured and shown alongside.
Reader Engagement
Steady Performance
13.8
/100
47 views
1 readers
AI Quality Assessment
Not analyzed
Readership in this journal
SteadyRanked #4 of 35 articles by views in International journal of advanced sciences and computing
Most read
Least read
Bar heights use a square-root scale.
Mint this article as an NFT
Not yet mintedCreate a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.
5
SUSD
one-off · no wallet required
Abstract
Financial institutions face a persistent arms race against increasingly sophisticated fraud, from card-not-present (CNP) transactions and account takeovers to synthetic identities and mule networks. This article surveys and systematizes machine-learning (ML) approaches for fraud detection across supervised, semi-supervised, and graph-based paradigms, with a focus on severe class imbalance, concept drift, and real-time constraints. We review data pipelines, feature engineering for transactional and device telemetry, and algorithmic choices (tree ensembles, margin-based models, deep learning, and graph neural networks). We discuss cost-sensitive learning, imbalanced evaluation (PR-AUC, MCC), explainability (SHAP/LIME), and privacy-preserving deployment (federated learning, differential privacy). A comparative illustration highlights the practical trade-offs among commonly used algorithms. We conclude with a roadmap that integrates MLOps, human-in-the-loop review, and regulatory compliance to reduce false positives while capturing evolving fraud patterns.
| Reference Key |
imported_1761903494_6904838649314
Use this key to autocite in the manuscript while using
SciMatic Manuscript Manager or Thesis Manager
|
|---|---|
| Authors | Ayesha Khalid, Muhammad Hamza Siddiqui, Sana Iftikhar |
| Journal | International journal of advanced sciences and computing |
| Year | 2022 |
| DOI |
DOI not found
|
| URL | |
| Keywords | Keywords not found |
Citations
No citations found. To add a citation, contact the admin at info@scimatic.org
Comments
No comments yet. Be the first to comment on this article.