AN EFFECTIVE PREDICTION SYSTEM FOR TIME SERIES DATA USING PATTERN MATCHING ALGORITHMS
S. Sridevi, Sudhaman Parthasarathy, S. Rajaram · International journal of industrial engineering · 2018
Demand for forecasting has increased significantly due to the rapid changes in technology, social changes, and globalization. The main objective of the paper is to apply clustering algorithms for forecasting the time series data. To perform the prediction, at first, the dataset is clustered and thus labeling is provided for samples in the dataset. For clustering, existing research works uses K-Means clustering algorithm (KM) despite the fact that this algorithm is more sensitive to initialization. To counter this limitation, K-Harmonic Means (KHM) algorithm is used in this research work for data clustering. Such clustering approaches are used to find pattern matching sequences in the samples. According to the window size, the pattern sequence is extracted from the samples. The value next to the matched sequence is extracted and Weighted Moving Average Method (WMAM) is applied to the extracted values. The WMAM gives the predicted value for the next day.