A SPEA-Based Group Trading Strategy Portfolio Optimization Algorithm.

Trading strategies are usually employed for finding trading signals for increasing returns as well as reducing risks. As a result, many approaches have been proposed for obtaining trading strategy portfolio. The group trading strategy portfolio (GTSP) optimization approaches that can be used to provide various trading strategy portfolios were also proposed. Because different criteria should be considered to derive GTSPs, a MOGA (multi-objective genetic algorithm) based approach has been presented for searching non-dominated solutions. In this paper, to extract a better set of non-dominated solutions, we propose a SPEA-based algorithm for deriving GTSPs with two objective functions. Since the goal of trading is to get profit, the first objective function is utilized to evaluate the return and risk of a candidate GTSP. The second objective function is used to evaluate whether the numbers of strategies between groups are similar and weights of groups as well. Experiments were conducted on a financial dataset to show the effectiveness of the proposed approach and comparison results of the proposed approach and the previous approach.