Evaluating business credit risk by means of approach‐integrating decision rules and case‐based learning

This research utilizes a new approach which uses a hybrid learning system that combines two representations of knowledge: the first in a form of decision rules referring to general knowledge, and the other of single cases corresponding to exceptions or untypical situations. The Explore algorithm was chosen as a tool for inducing general rules. It generates all simple and sufficiently strong general rules from a given data set. Examples discovered by these rules are then used to identify exceptions and untypical cases. The paper discusses problems connected with tuning parameters of this approach and introduces a new procedure for this task. This methodology is applied to solve the problem of evaluating the risk of business credit applications in a Polish commercial bank. Using information about business credit applications, as described by 35 economic parameters and using five groups of banking risk, a knowledge base consisting of 70 decision rules and 15 specific cases was induced. Testing this model in the standard ‘leaving‐one‐out’ way we achieved the best classification accuracy of 81%. A comparative study showed that results obtained by other machine‐learning algorithms resulted in significantly worse classification accuracy. Copyright © 2001 John Wiley & Sons, Ltd.     

Exponential moments for HJM models with jumps

General HJM models driven by a Lévy process are considered. Necessary moment conditions for the discounted bond prices to be local martingales are derived. Under these moment conditions, it is proved that the discounted bond prices are local martingales if and only if a generalized HJM condition holds. Research supported in part by Polish KBN Grant P03A 034 29 “Stochastic evolution equations driven by Lévy noise”.