Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Recurso digital |
| Lenguaje: | inglés |
| Publicado: |
Zenodo
2025
|
| Materias: | |
| Acceso en línea: | https://doi.org/10.5281/zenodo.15868373 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Tabla de Contenidos:
- <p>Detecting frauds in financial systems is crucial for cutting down losses and protecting the institution's reputation. With ever-increasing cases of financial frauds, the need for early detection of such cases has increased manifold. The paper proposes a machine learning approach for smart fraud detection with the specific goal of speeding up the verification process of checks to detect forgeries in time to prevent the occurrence of other damages. Various intelligent algorithms have been trained and tested on a public dataset that was resampled to address class imbalance; such a case is innate in fraud detection. By balancing the dataset, much better is the chance to accurately detect the fraudulent act.Experimental results show that the proposed machine learning models provide a very high performance in prediction, thus giving the banks enough time to mitigate any emergence of fraud. It is further stressed how AI can assist in bettering fraud detection, transaction security, and swift handing over suspicions in the banking sector.</p>