Fraud Identification in Financial Transactions: Machine Learning-Based Anomaly Detection Method
Bibliographic record
Abstract
Two major financial crimes that have reached epidemic proportions worldwide are credit card holder fraud and financial statement fraud. The efficacy of corporate governance, the calibre of financial reports, and the legitimacy of audit functions have all suffered from the collapse of well-known corporations. Credit card theft and financial statement fraud have grown to be serious problems for organizations worldwide. The predicted accuracy scores of Support Vector Classifiers (SVM) and Logistic Regression were found to be greater than those of the other classifiers employed in the unbalanced training dataset. An experimental model that first applies the class balancing technique to transform the unbalanced dataset into a balanced data set was developed in alignment with the research purpose and to design a model to improve results and reduce False Negative Rate. Using a nonlinear support vector machine model, a classifier was trained on the dataset. The AUC score of the suggested model was higher. By creating a new, selected hybrid class balancing technique and using the Random Forester algorithm to create an optimum classifier and analyse the outcomes, the experimental model of class balancing was further refined. Based on the results of this experiment, it was found that the suggested approach outperforms the prior model, generates a good AUC score, and maximizes false negatives. The approach can be used to address other comparable categorization issues for better results. It is not just restricted to online financial transactions; it also aids in lowering false negatives in credit card fraud transactions.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| 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) | 0.001 | 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".