Abstract
In this paper, a hybrid FOREX predictor model is developed by using a recurrent Legendre polynomial neural network (RLPNN) with an improved shuffled frog leaping (ISFL) based learning strategy. The recurrent network used in this study is a high order single layer neural network, structured using Legendre polynomials with feedback paths. The new recurrent network assembled integrating a functional expansion block with a delay block helps to map the internal nonlinearity associated with the input and output samples. Further a nature inspired learning strategy based on the memetic evolution of a team of frogs in search of their food locations is set forth to estimate the unrevealed parameters of the network. Empirically the model validation is realized over three currency exchange data sets accumulated within same period of time. Result investigation clearly illustrates the higher predictability of the proposed model compared to other models included in the study.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Journal of King Saud University - Computer and Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
