ABSTRACT Business loan is an important process and main revenue to bank. Loan asset is crucial in balance sheet. Asset quality is relevant to operating security, so bank should enhance the management and evaluation of loan process to ensure the operating security and performance during making a deal with clients. Sound evaluation model could help related staff evaluate the credit of clients and lower overdue loan ratio. IC industry is always the driving industry in Taiwan. Taiwan DRAM revenue, as a second place leader, accounts for more than 20% of world market. The nature of DRAM industry is huge capital, high technology level, fast price variation and those mean high risks during loan. Banks in Taiwan serve DRAM companies very often. In case of overdue loan, bank will be affected heavily. Thus, bank should build evaluation model of loan to ensure the security of loan. After reviewing related literature, this research identifies key factors of loan decision and invites related bank employees in north Hsin-Chu City to join AHP questionaire. Then this research conducts quantitative analysis through AHP. This research collects 16 bank professionals' opinions. Among 16 there are 6 Consistency Indexes higher than 0.1, so only 10 opinions are accepted. The result shows 3 main factors in loan evaluation: industrial evaluation, financial analysis and loan evaluation (listed in order). Besides, among overall criteria, the most important 5 are expansion of competitors' factory, ability to raise fund, quick ratio, new application, and collateral. This research proposes the following 4 suggestions: 1. Bank should ask professional industrial research institute for DRAM industrial evolution to reduce the credit risk. 2. The ability to raise fund is relevant to whether DRAM companies could get through the recession. Recent cash flow should be paid attention to. 3. The feasibility of capital expenditure plan should be evaluated as project finance and financial planning should be conducted with sensitivity analysis. 4. Risk cost should be considered when setting DRAM loan rate. Ensure return is consistent with the risk.

智慧型決策支援系統(Intellignet Decision Support Systems)的特點是可以同時處理定性和定量資料於同一個系統中，以同時執行各種知識推論及數量模式之運算。黑板架構(Blackboard Architecture)的做法是將決策支援求解過程的資料、模式和知識運用情形記錄於一共同工作區─稱之為黑板(Blackboard)，將模式及知識記錄在所謂的知識源(Knowledge Sources)中，並提供較有彈性之控制機制，應可提供較佳的解釋功能。以黑板架構為基礎的智慧型系統多應用在科學及工程方面，在管理方面卻寥寥無幾；管理問題多半屬於半結構性或非結構性，良好的解釋應為智慧型決策系統之重要功能。本研究擬就銀行業之授信審查做為本系統之專業領域知識(Domain Knowledge)，運用黑板架構中的階層化問題表現方式及模組化知識源分類之特性，建立提供完善解釋功能之智慧型授信決策支援系統。 / Incorporating artificial intelligence (AI) technique is critical to improve the functionality of decision support systems. Explanation function for consultation-based systems has been emphasized in the literature and should be considered important in developing intelligent decision support systems. Blackboard architecture can support a well-organized explanation facility due to its structurization of problem solving space, modularization of domain knowledge, and flexibility of reasoning control. Applying blackboard systems to managerial domain gets attention recently. Since most managerial consultation problems are unstructured or semi-structured, good explanation facility should be able to enhance the consultation effectiveness. The thesis investigates the potential of developing an explanation facility on the blackboard architecture using the loan evaluation as an example. During the interactive consultation process, the system can answer questions such as "What?", "Why?", "How?", and "Where?" with a friendly user interface. In terms of contribution, the inclusion of explanation facility can potentially increase the willingness and confidence of decision makers in using intelligent decision support systems. On the other hand, applying the graphic user interface to the development of explanation facility based on the blackboard architecture can make the reasoning process transparent and enhance the acceptance of this AI technique to managerial problem solving.