Artificial Intelligence-Powered Credit Card Fraud Detection: Feature Engineering and Machine Learning Approach’s
Bibliographic record
Abstract
The payment experience has been completely transformed by the use of cashless payment options including credit card purchases and web transactions, but it has also led to more sophisticated financial fraud, posing a significant challenge to payment system security. Accurately detecting fraudulent transactions while reducing false positives is a need for credit card fraud detection systems. use of a Convolutional Neural Network (CNN) model to detect fraudulent transactions is examined in this study using the Kaggle Credit Card Fraud Detection dataset. The CNN model performed quite well, with an F1 score of 79.52%, accuracy of 99.93%, precision of 80.8%, and recall of 78.29%. With a balanced trade-off between accuracy and recall, these findings demonstrate the model's capacity to detect fraud and manage unbalanced datasets. Further evidence of CNN's higher performance comes from comparison with other models, including k-Nearest Neighbours (k-NN) with Random Forest. This study demonstrates how advanced deep learning methods may be applied to effectively detect credit card fraud. Future research can explore hybrid models, advanced deep learning techniques, and domain-specific feature engineering to enhance model robustness and adapt to evolving fraud patterns.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".