Providing a Model for Predicting the Financial behavior of Currency Pairs in the Forex Market

Abstract

Objective: The present paper aims to achieve a suitable model for predicting the behavior of major currency pairs in the Forex market based on the chaos theory and a hybrid algorithm. Methods: This is an applied research study. The statistical population of the current study included the major currency pairs present in the Forex market having the largest trading shares (dollars, pounds, euros, and yen). The population comprised a total of 3,888 views i.e. 1,296 views for each currency pair. The trading period lasted from the beginning of January 2017 until the end of 2021. After examining the data and establishing the existence of chaos among the data, using two BDS tests and Lyapunov maximum view, three combined models were tested to achieve the best and most reliable status. Results: According to the results obtained from the BDS test and the maximum view of Lyapunov, there was chaos in the data of the three examined currency pairs. In addition, the chaos model with perceptron multilayer and elite non-dominant sorting genetic algorithm performed better than other models in this study. The values ​​of the Tails inequality coefficient and DM test statistics also indicated the hybrid superiority of the chaos model with perceptron multilayer and elite non-dominant genetic sorting algorithm. Conclusion: The results proved the chaos model with perceptron multilayer and elite non-dominant sorting genetic algorithm to be superior to the other two hybrid models.

Keywords

• behavior prediction
• forex
• modeling
• hybrid