Modelling Loan Classification as a Markov Chain

Résumé

Abstract This paper examined the loan portfolio classification criteria with the application of discrete time Markov chain. Default Portfolio were classify under three stage; Sub-standard, Doubtful and Loss in R programming. We predicted that Import and export from some specific classes states is possible with certain probabilities and stationary states distribution of 38 percent sub-standard, 33 percent Doubtful and 27 percent loss of a given portfolio at specific time period.

Citer ce document

Accès au document

Ce document est hébergé sur son dépôt institutionnel d'origine.

Auteur(s)

Statistiques

Consultations : 1

Téléchargements : 0