Wyniki wyszukiwania - BazTech

Ograniczanie wyników

1 Computer Science

1 2024

Powiadomienia systemowe

Sesja wygasła!
Sesja wygasła!

Znaleziono wyników: 1

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: fraud transactions

Sortuj według:

Ogranicz wyniki do:

Detection of credit card fraudwith optimized deep neuralnetworkin balanced data condition

Shome Nirupam, Sarkar Devran Dey, Kashyap Richik, Laskar Rabul Hussain

Computer Science

2024

T. 25 (2)

253--276

Due to the huge number of financial transactions, it is almost impossible forhumans to manually detect fraudulent transactions. In previous work, thedatasets are not balanced and the models suffer from overfitting problems. Inthis paper, we tried to overcome the problems by tuning hyperparameters andbalancing the dataset with a hybrid approach using under-sampling and over-sampling techniques. In this study, we have observed that these modificationsare effective in getting better performance in comparison to the existing models.The MCC score is considered an important parameter in binary classificationsince it ensures the correct prediction of the majority of positive data instancesand negative data instances. So, we emphasize on MCC score and our methodachieved an MCC score of 97.09%, which is far more (16 % approx.) than otherstate-of-the-art methods. In terms of other performance metrics, the result ofour proposed model has also improved significantly.