Prophesying the Short-Term Dynamics of the Crude Oil Future Price by Adopting the Survival of the Fittest Principle of Improved Grey Optimization and Extreme Learning Machine

Crude oil market analysis has become one of the emerging financial markets and volatility effect is paramount been considered as an issue utmost importance. This study examines dynamics this volatile crude by employing a hybrid approach based on extreme learning machine (ELM) regressor improved grey wolf optimizer (IGWO) for prophesying rate West Texas Intermediate (WTI) Brent datasets. The datasets are augmented using technical indicators (TIs) statistical measures (SMs) to obtain better insight into forecasting ability proposed model. differential evolution (DE) strategy used survival fittest (SOF) principle elimination while implementing GWO achieve convergence accuracy. Whereas, algorithmic simplicity, use less parameters, easy implementation DE efficiently decide evolutionary patterns wolves in SOF updates pack fitness value each wolf, thereby ensuring algorithm does not fall local optimum. Furthermore, comparison model with other models, such ELM–DE, ELM–Particle Swarm Optimization (ELM–PSO), ELM–GWO shows that predictability evidence obtained substantially achieves performance ELM–IGWO respect faster error mean square (MSE) during training testing phases. sensitivity provides results terms measures, Theil’s U, absolute (MAE), average relative variance (ARV), percentage (MAPE), minimal computational time.