Differential Evolution Algorithm for Solving the Portfolio Optimization Problem

Abstract

In the paper we develop metaheuristic method based on differential evolution for finding efficient frontier in solving the portfolio optimisation problem for investor with non concave utility function which reflects asymmetric investor attitude to losses and gains.

Basic methods of developing an expert system to assess the efficiency of power supply networks

“…When using the method of differential evolution in the process of developing an expert system, the number of populations, the maximum number of generations, the probability of change, and the probability of reduction cannot be given arbitrarily [9,10]. They have to be chosen by numerical experiments, with regard to the specifics of the task to be solved.…”

“…For control, the method of differential evolution, belonging to the class of stochastic methods of optimization and based on genetic algorithms with minor modifications, is used [11]. Based on the analysis of papers [7,8,10], it has been revealed that expert systems combine such advanced methods of artificial intelligence as methods of knowledge representation in a formalized form, methods of logical inference, scientific methods of heuristic search, recognition of sentences in natural language, etc.…”