Hybrid credit ranking intelligent system using expert system and artificial neural networks

Abstract

The main goal of all commercial banks is to collect the savings of legal and real persons and allocate them as credit to industrial, services and production companies. Non repayment of such credits cause many problems to the banks such as incapability to repay the central bank's loans, increasing the amount of credit allocations comparing to credit repayment and incapability to allocate more credits to customers. The importance of credit allocation in banking industry and it's important role in economic growth and employment creation leads the development of many models to evaluate the credit risk of applicants. But many of these models are classic and are incapable to do credit evaluation completely and efficiently. Therefore the demand to use artificial intelligence in this field has grown up. In this paper after providing appropriate credit ranking model and collecting expert's knowledge, we design a hybrid intelligent system for credit ranking using reasoning-transformational models. Expert system as symbolic module and artificial neural network as non-symbolic module are components of this hybrid system. Such models provide the unique features of each components, the reasoning and explanation of expert system and the generalization and adaptability of artificial neural networks. The results of this system demonstrate hybrid intelligence system is more accurate and powerful in credit ranking comparing to expert systems and traditional banking models.

A hybrid neural network approach for credit scoring

“…Zhang et al (1999) also found ANN significantly better than LR in bankruptcy prediction. To further enhance the performance of ANN, several researches had endeavoured to integrate ANN with other classification methods and reached the conclusion that hybrid design architectures were capable of obtaining a more accurate classification (Gopalakrishnan et al , 1995; Sung, 1998; Lee et al , 2002; Lee & Chen, 2005; Bahrammirzaee et al ., 2009).…”

Credit modelling using hybrid machine learning technique

“…The hybrid and ensemble models are efficient and robust because they combines the complementary features of more than one learning technique and overcomes the weakness of individual techniques. The hybrid models can be stand alone, transformational, tightly coupled or fully coupled [9]. As per [10] hybrid models are of 4 types: Classification combined with Classification, Classification combined with Clustering, Clustering combined with Clustering and Clustering combined with Classification.…”

Diseño de un modelo basado en redes neuronales en la nube para determinar el riesgo de crédito en los solicitantes de microcrédito en el mercado financiero de Perú

“…Debido a la importancia del riesgo de crédito para las entidades financieras, se han desarrollado diversas investigaciones, según las Referencias [6], [7], [10], [11] tendientes a aumentar la exactitud de la predicción del riesgo crediticio. A partir del 2005 han tomado mayor importancia los modelos basados en técnicas de inteligencia artificial, porque han demostrado tener mayor precisión en la predicción del riesgo crediticio.…”

“…En la Ref. [7], se eligen redes neuronales artificiales y sistemas expertos para construir un sistema híbrido inteligente para la clasificación de crédito. Se desarrolla un sistema híbrido para combinar las capacidades de ambos sistemas.…”