Detecting Time Correlations in Time-Series Data Streams

In this paper, a novel method for analyzing time-series data and extracting time-correlations among multiple time-series data streams is described. The time-correlations tell us the relationships and dependencies among time-series data streams. Reusable time-correlation rules can be fed into various analysis tools, such as forecasting or simulation tools, for further analysis. Statistical techniques and aggregation functions are applied in order to reduce the search space. The method proposed in this paper can be used for detecting time-correlations both between a pair of time-series data streams, and among multiple time-series data streams. The generated rules tell us how the changes in the values of one set of time-series data streams influence the values in another set of time-series data streams. Those rules can be stored digitally and fed into various data analysis tools, such as simulation, forecasting, impact analysis, etc., for further analysis of the data.