Multi–objective Evolutionary Algorithms for the Risk–return Trade–off in Bank Loan Management

Multi–criteria decision–making is an increasingly accepted tool for decision–making in management. In this work, we highlight the application of a novel multi–objective evolutionary algorithm, NSGA–II, to the risk–return trade–off for a bank–loan portfolio manager. The manager of a bank operating in a competitive environment faces the standard goal of maximizing shareholder wealth. Specifically, this attempts to maximize the net worth of the bank, which in turn involves maximizing the net interest margin of the bank (among other factors, such as non–interest income). At the same time, there are significant regulatory constraints placed on the bank, such as the maintenance of adequate capital, interest–rate risk exposure, etc. The genetic algorithm–based technique used here obtains an approximation to the set of Pareto–optimal solutions which increases the decision flexibility available to the bank manager, and provides a visualization tool for one of the trade–offs involved. The algorithm is also computationally efficient and is contrasted with a traditional multi–objective function — the epsilon–constraint method.