Building expert systems
Why Prolog? Justifying logic programming for practical applications
Why Prolog? Justifying logic programming for practical applications
Meta-programming in logic programming
Meta-programming in logic programming
The art of Prolog (2nd ed.): advanced programming techniques
The art of Prolog (2nd ed.): advanced programming techniques
From logic programming to Prolog
From logic programming to Prolog
Integrated research components: a practical and effective alternative to senior projects
Journal of Computing Sciences in Colleges
Hi-index | 0.00 |
We present an expert system, Credit Evaluation and Explanation Expert System (CEEES), that decides whether to grant credit lines to applicant firms. CEEES, which is developed in Prolog, uses a meta-level interpreter to generate proofs for its decisions. The rule-based language used by CEEES enables the various models and decision-making processes used by individual financial institutions to be easily incorporated into the knowledge base, allowing adaptability for commercial ventures. We evaluate the credit-worthiness of applicant firms according to a theoretical model advanced in the economics and credit-risk management literature. The default probabilities of applicant firms are computed using empirical data on customer default grouped according to ratings similar to Standard & Poor's ratings. The ratings are assigned using qualitative threshold rules that consider business credit history, asset size and liquidity, debt capacity, quality of management, market reputation, and position in market. The default probability is multiplied by the exposure at default and the loss given default to determine the expected loss. Unless the expected benefit is large enough to both subsume this expected loss and generate sufficient revenue for the financial institution, CEEES will recommend that the application for a credit line be rejected.