A hybrid model based on variational autoencoders and PCA for credit card fraud detection

A hybrid model based on variational autoencoders and PCA for credit card fraud detection

Credit card fraud detection poses a significant challenge due to extreme data imbalance, where fraudulent transactions represent less than 0.2% of the total. This study propo ses a hybrid approach that combines a Variational Autoencoder (VAE) for unsupervised feature learning, Principal Component An...

Deskribapen osoa

Gorde:
Xehetasun bibliografikoak
Egile nagusia: Caicedo García, Kevin Omar (author)
Formatua: masterThesis
Argitaratua: 2025
Gaiak:
Detección de Fraudes
Autoencodificador Variacional
Desbalance de Clases
Fraud detection
Variational autoencoder
Class Imbalance
Sarrera elektronikoa:https://repositorio.yachaytech.edu.ec/handle/123456789/1043
Etiketak: Etiketa erantsi
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!

Internet

https://repositorio.yachaytech.edu.ec/handle/123456789/1043

Antzeko izenburuak