Method for creating period profile for time-series data with recurrent patterns

One or more non-transitory computer-readable media storing instructions, which, when executed by one or more hardware processors, cause performance of operations comprising:

• receiving a set of time series data that includes data spanning a plurality of time windows having a seasonal period;
• associating, based at least in part on the set of time series data, a first set of sub-periods of the seasonal period with a particular class of seasonal pattern;
• wherein, after associating the first set of sub-periods with the particular class of seasonal pattern, a second set of sub-periods is not associated with the particular class of seasonal pattern;
• generating a forecast based at least in part on which sub-periods of the seasonal period are associated with the particular class of seasonal pattern;
• and
• performing, by one or more computing devices, one or more seasonal-aware operations based at least in part on the forecast.

A system comprising:

• one or more hardware processors;
• one or more non-transitory computer-readable media storing instructions, which, when executed by one or more hardware processors, cause performance of operations comprising:
• receiving a set of time series data that includes data spanning a plurality of time windows having a seasonal period;
• associating, based at least in part on the set of time series data, a first set of sub-periods of the seasonal period with a particular class of seasonal pattern;
• wherein, after associating the first set of sub-periods with the particular class of seasonal pattern, a second set of sub-periods is not associated with the particular class of seasonal pattern;
• generating a forecast based at least in part on which sub-periods of the seasonal period are associated with the particular class of seasonal pattern;
• and
• performing, by one or more computing devices, one or more seasonal-aware operations based at least in part on the forecast.