Among the different data mining techniques which can be used to extract knowledge from numerical data, the nearest neighbor approach has been widely applied in many mathematical and statistical problems. In this paper we use an algorithm based on a modified version of the nearest neighbor method to solve a problem of classifying the creditworthy clients, in a banking context. The empirical analysis is undertaken by considering data from an Italian local bank.
A nearest neighbor approach for a credit classifiction problem
FUNARI, Stefania;GIOVE, Silvio
2002-01-01
Abstract
Among the different data mining techniques which can be used to extract knowledge from numerical data, the nearest neighbor approach has been widely applied in many mathematical and statistical problems. In this paper we use an algorithm based on a modified version of the nearest neighbor method to solve a problem of classifying the creditworthy clients, in a banking context. The empirical analysis is undertaken by considering data from an Italian local bank.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
A nearest neighbor-Rendiconti.pdf
non disponibili
Tipologia:
Documento in Pre-print
Licenza:
Accesso chiuso-personale
Dimensione
223.14 kB
Formato
Adobe PDF
|
223.14 kB | Adobe PDF | Visualizza/Apri |
I documenti in ARCA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
