Credit Card Fraud Detection Using Deep Learning
| Autor: | Anu Maria Babu, Anju Pratap |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Artificial neural network
business.industry Computer science Interface (computing) Deep learning Feature extraction Credit card fraud ComputingMilieux_LEGALASPECTSOFCOMPUTING Machine learning computer.software_genre Convolutional neural network ComputingMethodologies_PATTERNRECOGNITION False positive paradox Artificial intelligence business Transaction data computer |
| Zdroj: | 2020 IEEE Recent Advances in Intelligent Computational Systems (RAICS). |
| Popis: | This paper discusses a method in the fraud detection interface area. The approach proposed is to use imbalanced highly skewed transactional data and a convolutional network for the detection of frauds. The dataset used here is the machine learning kaggle dataset for credit card fraud detection that contains highly skewed data. The evaluated features are 1 for fraud and 0 for non-fraud class. The analysis of fraud detection was an important tool in banking sectors. Nowadays, the artificial neural network has become the least successful method for credit card fraud detection. The system currently used to detect fraud is plagued by misclassifications and highly false positives. In such situations here this research paper uses the in cooperation of convolutional neural network layers in an attempt to build a model for detecting credit card fraud that gives us a high level of accuracy. The goal is to predict fraud under 300 epochs, the current approach can be classified accurately at 99.62 %. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|