SURVIVAL ANALYSIS AS A TOOL FOR BETTER PROBABILITY OF DEFAULT PREDICTION

Abstract

This paper focuses on using survival analysis models in the area of credit risk and on the modellingof the probability of default (i.e. a situation where the debtor is unwilling or unable to repay the loanin time) in particular. Most of the relevant scholarly literature argues that the survival modelsproduce similar results to the commonly used logistic regression models for the development ortesting of samples. However, this paper challenges the standard performance criteria measuringprecision and performs a comparison using a new prediction-based method. This method givesmore weight to the predictive power of the models measured on an ex-ante validation samplerather than the standard precision of the random testing sample. This new scheme shows thatthe predictive power of the survival model outperforms the logistic regression model in termsof Gini and lift coefficients. This finding opens up the prospect for the survival models to be furtherstudied and considered as relevant alternatives in financial modelling.