Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100090, China
Copyright © 2009 Yue Tang et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Classification of whether recovery of non-performing loans (NPL) is zero or positive is not only important in management of non-performing loans, but also is essential for estimating recovery rate and implementing the new Basel Capital Accord. Based on the largest database of NPL's recovering information in China, this paper tries to establish discriminant models to predict the loan with zero recovery. We first use Step-wise discrimination method to select variables; then give an in-depth analysis on why the selected variables are important factors influencing whether a loan is zero or positive recovery rate. Using the selected variables, we establish two-type discriminant models to classify the NPLs. Empirical results show that both models achieve high prediction accuracy, and the characteristics of obligors are the most important factors in determining whether a NPL is positively recovered or zero recovered.