The problem of credit card fraud detection is approached by a semi-supervised classification task on a data stream. The DISSFCM algorithm is applied, which is based on Dynamic Incremental Semi-Supervised Fuzzy C-Means that processes data grouped in small-size chunks. Experimental results on a real-world dataset of credit card transactions show that DISSFCM has comparable results with some fully-supervised stream data classification methods, also in presence of a high percentage of unlabeled data.
Credit card fraud detection by dynamic incremental semi-supervised fuzzy clustering
Gabriella Casalino;Giovanna Castellano;Corrado Mencar
2019-01-01
Abstract
The problem of credit card fraud detection is approached by a semi-supervised classification task on a data stream. The DISSFCM algorithm is applied, which is based on Dynamic Incremental Semi-Supervised Fuzzy C-Means that processes data grouped in small-size chunks. Experimental results on a real-world dataset of credit card transactions show that DISSFCM has comparable results with some fully-supervised stream data classification methods, also in presence of a high percentage of unlabeled data.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.