Dynamically controlled processing of time series datasets based on the detection of stationary time series grains

A computer-readable storage medium for managing a time series dataset that includes a number of time series grains, the computer-readable storage medium having encoded thereon computer-executable instructions to cause one or more processing units of a system to:

• receive the time series dataset;
• determine a threshold value;
• analyze the time series grains to identify a number of stationary time series grains;
• determine that a ratio of the number of the stationary time series grains and a total number of grains in the time series dataset is below the threshold value;
• in response to determining that the ratio of the number of the stationary time series grains and the total number of grains in the time series dataset is below the threshold value:
• cause an execution of computational operations for performing a differencing function to the time series dataset, the execution of the computational operations for performing the differencing function causing a generation of an output dataset, the output dataset comprising modified grains that are generated from the differencing function applied to the time series grains of the time series dataset;
• and utilize the output dataset to train a model used for generating forecasting data.

A computing device for managing a time series dataset that includes a number of time series grains, comprising:

• one or more processing units;
• and
• a computer-readable storage medium having encoded thereon computer-executable instructions to cause the one or more processing units to:
• receive the time series dataset;
• determine a threshold value;
• analyze the time series grains to identify a number of stationary time series grains;
• determine that a ratio of the number of the stationary time series grains and a total number of grains in the time series dataset is below the threshold value;
• in response to determining that the ratio of the number of the stationary time series grains and the total number of grains in the time series dataset is below the threshold value:
• cause an execution of computational operations for performing a differencing function to the time series dataset, the execution of the computational operations for performing the differencing function causing a generation of an output dataset, the output dataset comprising modified grains that are generated from the differencing function applied to the time series grains of the time series dataset;
• and
• utilize the output dataset to train a model used for generating forecasting data.