Time series long-term forecasting model based on information granules and fuzzy clustering

In spite of the impressive diversity of models of time series, there is still an acute need to develop constructs that are both accurate and transparent. Meanwhile, long-term time series prediction is challenging and of great interest to both practitioners and research community. The role of information granulation is to organize detailed numerical data into some meaningful, semantically sound entities. With this regard, the design of time series forecasting models used the information granulation is interpretable and easily comprehended by humans. In order to cluster information granules, a modified fuzzy c-means which does not require that data have the same dimensionality is proposed. Then, we develop forecasting model combining the modified fuzzy c-means and information granulation for solving the problem of time series long-term prediction. Synthetic time series, chaotic Mackey-Glass time series, power demand, daily temperatures, stock index, and wind speed are used in a series of experiments. The experimental results show that the proposed model produces better forecasting results than several existing models. HighlightsTime series is translated into semantically sound information granules.A modified fuzzy c-means based on dynamic time warping is proposed.The multiple fuzzy rules interpolation is applied to determine predicting variation.Chaotic Mackey-Glass, power demand, and daily temperatures time series are chosen.The results show that the proposed model is both accurate and interpretable.