10-08-2016 07:14 AM
Can you help me with the following problem?
I wish to construct a Markov Transition Matrix [ within Credit Risk Roll Rate Analysis ]
Basically the idea is to use empirical customer payment data to estimate the probability of a customer changing
their delinquency state within a unit of time (a month) and to embed this information in a Markov Transition Matrix.
I am looking for a SAS Macro or Program that will enable me to construct the Transition Matrix from the monthly
customer behavioural / payment data.
Possible delinquency states are as follows:
S1: Performing [ 0 to 5 Days in Arrears ]
S2: Early Stage Delinquency [ 5 to 30 Days in Arrears ]
S3: Early Stage Delinquency [ 31 to 59 Days in Arrears ]
S4: Late Stage Delinquency [ 60 to 89 Days in Arrears ]
S5: In Default [ Greater than 89 Days in Arrears ]
S6: Termination of Contract: [ Absorbing State ? ]
S7: Foreclosure / Repossession [ Absorbing State ? ]
I would appreciate any suggestions or advice that you are able to provide.
10-08-2016 08:20 AM
Just to be clear, your goal is to estimate the transition probabilities from data?
Please post example data that shows the structure of your data.
10-08-2016 12:00 PM