Application of BP algorithm in credit risk analysis
Sulin Pang · Control theory & applications · 2005
A credit-risk evaluation model is established,which is based on back-propagation (BP) algorithm.The model has been applied to evaluate the credits of 80 applicants in a commercial bank of our country in 2001.These data are separated into two groups:a good group and a bad group according to their finance,management and previous credit records.As to each applicant,seven financial rates are considered that can reflect its debt paying ability,profitability,quality of management and capital structure. The BP network is trained 100,390 and 800 times respectively.The simulations show that,when the network is trained 800 times,it enters steady state and the performance function reaches optimal value,and the classification accuracy rate is 98.75%.In addition,a learning algorithm and steps of the BP network are presented as well.