Neural network survival analysis for personal loan data

Traditionally, customer credit scoring aimed at distinguishing good payers from bad payers at the time of the loan application. However, the timing when customers become bad is also very interesting to investigate since it can provide the bank with the ability to compute the profitability over a customer's lifetime and perform profit scoring. The problem statement of analysing when customers default is commonly referred to as survival analysis. It is the purpose of this paper to discuss and contrast statistical and neural network approaches for survival analysis in a credit-scoring context. When compared to the traditional statistical proportional hazards model, neural networks may offer an interesting alternative because of their universal approximation property and the fact that no baseline hazard assumption is needed. Several neural network survival analysis models are discussed and evaluated according to their way of dealing with censored observations, time-varying inputs, the monotonicity of the generated survival curves and their scalability. In the experimental part of this paper, we contrast the performance of a neural network survival analysis model with that of the well-known proportional hazards model for predicting both loan default and early repayment using data from a U.K. financial institution.