Modelling and Forecasting of Monthly Crude Palm Oil Price of Malaysia using Hybrid Wavelet-Modified GMDH Model

This study comprises developing a more appropriate hybrid wavelet-modified GMDH model for forecasting the monthly crude palm oil (CPO) price of Malaysia. In proposed model, complex data CPO is decomposed into different sub series using discrete wavelet transform (DWT) and then it has been linked with modified model. Sigmoid, radial basis, tangent polynomial functions are selected as transfer in best fit correct compared to conventional GMDH. The were taken from Malaysian Palm Oil Board (MPOB) spanning period January 1983 November 2019. capabilities modelling determined by MAE, RMSE, MAPE, R R2. MAPE Malaysia less than 4 % coefficient correlation (R) 0.99, which show an excellent individual provides alternative tools help industry deal variations assists playing dominant role worldwide international market.