MétaCan
Menu
Back to cohort
Record W4407421575 · doi:10.62754/joe.v4i2.6377

Advanced Machine Learning Approaches for Credit Card Fraud Detection in the USA: A Comprehensive Analysis

2025· article· en· W4407421575 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueJournal of Ecohumanism · 2025
Typearticle
Languageen
FieldComputer Science
TopicImbalanced Data Classification Techniques
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsCredit card fraudCredit cardComputer scienceComputer securityMachine learningBusinessData scienceArtificial intelligenceWorld Wide Web

Abstract

fetched live from OpenAlex

Credit card fraud is a financial threat in America, both for financial institutions and for consumers, and it is growing in severity. Traditional fraud detection methods become less effective in countering emerging fraud trends, and for that reason, sophisticated algorithms in machine learning have to be embraced. This research project strived to develop and compare complex algorithms for fraud detection in credit cards in America. With a variety of algorithms including both unsupervised and supervised learning, this study strived towards improving fraud transaction detection rates. This study focuses on real-world credit card transaction datasets from America, offering a robust foundation for comprehending the intricacies of fraud detection in an authentic financial context. Employing actual transaction data, the study aims to replicate and model variation and nuance in fraud and consumer behavior, such that any developed machine learning algorithms will have a basis in real-life realities. For model selection, we deployed several machine learning models, notably Logistic Regression, Random Forest, and XG-Boost Classifier. In evaluating model performance, several key metrics, including Precision, Recall, and the F1-score, were taken into consideration. Random Forest Classifier performed best overall, with relatively high accuracy for fraud prediction, and average recall, with a marginally high level of F1-score. Overall, it can be noticed that Random Forest has the most balanced performance out of the three in fraud detection capabilities, which seems to be a necessity. The integration of real-time fraud prevention with machine learning models is revolutionizing financial institution transaction monitoring. ML models can analyze and process information in real-time, and thus, allow for effective and efficient real-time fraud monitoring. The future of fraud detection holds many exciting avenues for research, most prominently in deep model development. Methods in deep learning, such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs), have been successful in discovering complex structures and sequential relations in transactional information. Another promising avenue for future research is combining AI-powered identity verification with blockchain technology for fraud prevention.

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.

Full frame distilled prediction

Teacher imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.932
Threshold uncertainty score0.314

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.054
GPT teacher head0.299
Teacher spread0.245 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it