An Improved Weighted Moving Average Methods Based on Transferring Weights for an Analytical Process Data

Time series forecasting is an active research area that has drawn considerable attention for applications in a variety of areas. Moving Average is one of widely known technical indicator used to predict the future data in time series analysis. During its' development, many variation and implementation have been made by researchers. One of its' widely used variation is Weighted Moving Average that gives a special weighting to more recent data than the older data, which could not be found in Simple Moving Average method. This paper aims to introduce a new approach of moving average method in time series analysis. The approach will propose transferring weights mothod as the new weighting factor in view of the lagging and incomplete problems of the weighted moving average method. Both theoretical and empirical findings have suggested that the proposed method can be an effective method of improving upon their predictive performance, especially when the models in improving the lagging and Outburst value. In this paper, the models are implemented in order to overcome data limitations of weighted moving average models, thus obtaining more accurate results. Experimental results of Water Injection in oil field indicate that the models exhibit effectively improved forecasting accuracy so that the model proposed can be used as an alternative to forecasting tools. The result of the proposed method shows a promising result in this preliminary work.