Using Feedback-Matching Algorithm in Time Series Future Values Prediction

Time series data is employed for the representation of observations of many economic, social, and engineering phenomena. Casting Mary goal of studying time series is to predict the behavior of the series in the future, as forecasting has a large and effective role in many topics and various applications. The process forecasting the future determining the values of the time series is usually done using the general trend equation, which constitutes an artificial view of the time series, due to its distance from the natural form of the time series by a certain percentage, this work proposed to deal with the time series by its natural view; that is, dealing with the data as it is without any representation in mathematical formulas, and to achieve the prediction process, the paper provided an algorithm that called the feedback-matching algorithm, which can use the natural form of the data string to form the prediction procedure. Comparing the outcomes of the suggested algorithm with the outcomes of the most important methods used in this field, it was given that the results of this algorithm are close, and in some cases better than the results of the traditional methods.