Combining an expert system with simulation to enhance planning for banking networks

Abstract

This application paper shows how bankers who are planning to operate a local electronic funds transfer (EFT) network can use simulation and an expert system to improve their EFT decisions. The key to making good EFT decisions is understanding the tradeoffs between the costs and performance of different network possibilities. Being able to explore network choices in light of a bank's service and profit goals, prior to the actual commitment of resources, is essential to that understanding. However, there are no published EFT studies which attempt to combine both technical and economic con cerns, particularly the representation of intangible benefits and costs, in a single methodology. The simulation process de scribed here illustrates a computer model that approximates the performance and economics of alternative local EFT designs. Expert system technology is incorporated to give bankers the convenience of interacting with the model in a natural language format. It should be noted that the work described here is based on the author's current research and ongoing model development for client banks. Every attempt is made to be as informative as possible without breaching confidentiality.