A Perceptron Based Neural Network Data Analytics Architecture for the Detection of Fraud in Credit Card Transactions in Financial Legacy Systems
Bibliographic record
Abstract
Credit card fraud, a significant and growing problem in commerce that costs the global economy billions of dollars each year, has kept up with technological advancements as criminals devise new and innovative methods to defraud account holders, merchants, and financial institutions. While traditional fraudulent methods involved card cloning, skimming, and counterfeiting during transactional processes, the rapid adoption and evolution of Internet technologies aimed at facilitating trade has given rise to new digitally initiated illegitimate transactions, with online credit card fraud beginning to outpace physical world transactions. According to the literature, the financial industry has used statistical methods and Artificial Intelligence (AI) to keep up with fraudulent card patterns, but there appears to be little effort to provide neural network architectures with proven results that can be adapted to financial legacy systems. The paper examines the feasibility and practicality of implementing a proof-of-concept Perceptron-based Artificial Neural Network (ANN) architecture that can be directly plugged into a legacy paradigm financial system platform that has been trained on specific fraudulent patterns. When using a credit checking subscription service, such a system could act as a backup.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".