Foreign Exchange Market Analysis based on Novel Grey Wolf based Extreme Learning Machine Predictor

Foreign exchange trading basically bridges a gap between buyer and seller to transact at a set of prices of the currencies to make profit out of it by the traders and investors. In this paper, foreign exchange predictive models are explored based on basic Extreme Learning Machine (ELM) along with optimized version of ELM. Initially, this work tried to obtain the best optimized ELM network based upon the four nature-inspired optimization methodologies such as; particle swarm, ant colony, moth flame and grey wolf optimization (GWO). From this phase, it has been observed that the ELM network optimized with GWO outperforms rest of other experimented optimized ELM networks with respect to error graphs and performance metrics. In order to evaluate the performance, the ELM-GWO currency exchange predictor, the recognition performance metrics such as; EVS, MAE, MSE and R
²
Score are computed, the error graphs are obtained and the average computational time taken are compared.