Fuzzy and neuro-symbolic approaches in personal credit scoring: Assessment of bank loan applicants

Abstract

Credit scoring is a vital task in the financial domain. An important aspect in credit scoring involves the assessment of bank loan applications. Loan applications are frequently assessed by banking personnel regarding the ability/possibility of satisfactorily dealing with loan demands. Intelligent methods may be employed to assist in the required tasks. In this chapter, we present the design, implementation and evaluation of two separate intelligent systems that assess bank loan applications. The systems employ different knowledge representation formalisms. More specifically, the corresponding intelligent systems are a fuzzy expert system and a neuro-symbolic expert system. The former employs fuzzy rules based on knowledge elicited from experts. The latter is based on neurules, a type of neuro-symbolic rules that combine a symbolic (production rules) and a connectionist (adaline unit) representation. A characteristic of neurules is that they retain the naturalness and modularity of symbolic rules. Neurules were produced from available patterns. Evaluation showed that the performance of both systems is close although their knowledge bases were derived from different types of source knowledge. © 2014 Springer International Publishing Switzerland.