Expert System for Evaluating And Supporting Credit Decisions For the Banking Sector

Abstract

The problem of this study is that the phenomena of over due debts are a major problem to the banks in the field of bank credit. The banks crises studies in different countries, whether advanced or developed, point out that most of the countries which are exposed to financial crises are due to the main reason of the over due credits (financial defaults). It is worth mentioning that 131 countries suffered from bank crises, which differ in its magnitude during the period (1975 - 2000). The losses that resulted from credit risk are not only restricted to direct accounting losses, but also extend to include opportunity cost, operations costs, and band debts related expenses. Most major banking problems have been either explicitly or indirectly caused by weakness in credit risk management. The reasons for this problem can be summarized in the following points: concentration of bank credit to a minority of clients, the credit processing, market and liquidity- sensitive exposures, and inadequate monitoring. Basel Committee on Banking Supervision emphasized this as an important aspect of credit risk. The banks face very challenging and important financial problems. These problems appear in the last few years. The reasons for these problems are mainly due to the lack in using good credit ratings and assessment, which might indicate a high risk of defaulting on a loan, and thus leads to high interest rates. In turn, the high interest rates may cause companies or individuals to default in the repayment of the loans in the agreed period, determined by bank. In other words, there will be a financial failure, because of the weakness in credit-risk assessment by the bank granting the credit. In the Banking System, there has always been a lack of, and insufficient analysis of the financials of the credit applicants. In addition, banks face credit risks because of weak feasibility studies presented to them, plus the fact that the collaterals accepted were mainly insufficient, as well as the absence of an efficient controlling system by the banks.

The objectives of this thesis are: a) To investigate the possibility of developing an expert system tool that includes the knowledge of the bankers' experts in the domain of bank credit, plus the literature on banks credit risks. This tool is intended to aid the decision maker to issue the right decision with familiar and easy-to-use interfaces, which allows for encoding the knowledge in a simple way. b) The expert system must assess the financial position of an applicant. This requires analysis of both quantitative and qualitative information on the financials of the company. Moreover, the economic aspects, which consist of the global economic conditions, the national economic and political conditions, and the social impact of the project, should also be considered. In addition, the marketing and technical feasibility studies aspects must be considered. Moreover, collaterals must be taken into consideration as risk mitigation. c) The expert system must evaluate the credit application with the view of avoiding the possibility of over due debts (financial defaults). d) The expert system should help in reducing the time devoted to the analysis of the credit application, and improves quality of the evaluation which would produce substantive benefits to the banks using the system. In general, the main objective of the expert system is to use both quantitative and qualitative information in order to capture as closely as possible the experience of the recognized experts in the field of banking credit.

The banks traditional systems were failed to give the correct credit decisions, which was obvious in the table 1-1 in the section of the statement of the problem. Therefore, the importance of this study stems from the following points: a) There are no an expert systems in supporting credit decisions that are applied in the Sudan. b) There is a big need for those systems in the banks sector, exactly in management of risks in the banks. c) Relying on an expert system in supporting credit decisions reduces the phenomenon of the over due debts (financial default) and helps in the socio-economic development. d) The expert system in supporting credit decisions will help in allocating efficiently the scarce financial resources that are pooled in the Banking Sector. The methodology that is used is the CommonKADS (Knowledge Acquisition Development Systems). The major contribution of this study is to propose an expert system for evaluating and supporting credit decisions on the banking sector (ESESCD). This type of system has never been introduced into the Sudan before. And the evaluation process has taken into consideration all the variables that need to be considered in the decisions of the banking credit, which was not dealt with in all such expert systems even internationally. The most important results that has emerged from this study is that: (1) The proposed expert system has achieved the objectives of the study. (2) The expert systems can help efficiently and objectively why a particular decision in granting credit is made. (3) It can eliminate any weaknesses in the traditional procedures of credit assessment and granting of a loan. (4) It can evaluate objectively the credit-worthiness of the applicants of bank loans. (5) It can objectively help in assessing and determining the risks associated to all loans. (6) The Expert System is designed to give logical justifications for the decisions made regarding the granting or rejection of the credit applications. (7) The designed expert system is very flexible, and it can accommodate any new variables that may arise in credit decisions including weight for the different parts that affect the credit decision. (8) This system is very easy to apply and hence help decision makers to take the right decisions in a very short period, in other words using such a system is economical to all banks. (9) By testing the system on tow real credit application cases it gave decisions and justifications that can help banks to avoid credit risks. (10) The expert systems have unlimited potentials to assist financial institutions in their future work. (11) They can be used to train new employees to improve their efficiency to conduct their duties. The main recommendations of this thesis are: 1. Such a system is recommended to be used by all types of banks in assessing credit applications, because it is economical and easy to apply. 2. The system can easily be adjusted to accommodate all the requirements needed by all financial institutions. 3. The banks must not grant credit without preparing accurate studies to avoid the over due debts phenomenon. 4. The banks when granting credit should flow logical system which will reduce the risk of over due debts. The most important future works that has emerged from this study can be summarized in the following: 1- As an extension of this thesis the decision support system can be used in other financial and non financial fields after adjusting it to suit the purposes of such fields. 2- The expert system can be used by scholars to strengthen their analytical ability and communicational skills, plus improving the research skills of university students who attempt to design such systems.