Soft multicriteria computing supporting decisions on the Forex market

The paper relates to decisions made by traders on the Forex market. Existing trading systems based on technical analysis use crisp relations-binary activation functions to generate BUY or SELL signals for the trader. A large number of signals generated independently by different indicators and relatively low accuracy of the signals is observed, so that they cannot be effectively used in decision-making processes. A new fuzzy multicriteria approach is proposed in this paper. It includes the application of the theory of fuzzy systems and multicriteria analysis. The crisp relations are replaced by fuzzy ones. The signals generated by different indicators at the same time are analyzed in a multicriteria space. Each criterion relates to different indicator with the value defined by a respective membership function. A multicriteria optimization problem is formulated in which the currency pairs - variants in the analysis, having maximum values of all criteria are looked for. An original dominance-based algorithm is presented. It calculates a selected set of non-dominated variants that can be presented to the trader. A computer-based system is constructed on the basis of the proposed approach and including the proposed algorithm. The system having data from the market derives selected variants for further analysis and also check their prediction accuracy. Numerical experiments on real data from the Forex market show advantages of the proposed approach in comparison to the existing traditional crisp systems. (C) 2020 Elsevier B.V. All rights reserved.