On the fusion of regression and neural network methods

Abstract

In this paper, a cascade forward neural network model and a quadratic regression model are fused together to form a hybrid model that was applied on the daily crude oil production data of the Nigerian National Petroleum Corporation (NNPC) to forecast the daily crude oil production of the NNPC. The fusion was made possible by the Bayesian model averaging technique, which was used to obtain a combined forecast from the two separate methods, that is, the cascade forward backpropagation neural network method and the quadratic regression method. The model resulting from the fusion was applied on the difference series. The results indicate that the combined forecast have better forecasting performance greater than the standalone methods on the difference series based on the mean square error sense. The root mean square error (RMSE) and the mean absolute error (MAE) were applied to ascertain the assertion that the combined forecast has better forecasting performance greater than the standaloneforecast. The analysis for this study was simulated using MATLAB software, version 8.03.