Patent · US Active

Methods for self-adaptive time series forecasting, and related systems and apparatus

US11250449B1 · kind B1 · utility

1Cited by
31References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 9, 2019
Grant dateFeb 15, 2022
Priority date
Expiry dateJul 9, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06Q10/06395
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

An apparatus has a memory with processor-executable instructions and a processor operatively coupled to the memory. The apparatus receives datasets including time series data points that are descriptive of a feature of a given entity. The processor determines a time series characteristic based on the data content, and selects, based on the determined characteristic, a set of entrant forecasting models from a pool of forecasting models stored in the memory. Next, the processor trains each entrant forecasting model with the time series data points to produce a set of trained entrant forecasting models. The processor executes each trained entrant forecasting model to generate a set of forecasted values indicating estimations of the feature of the given entity. Thereafter the processor selects at least one forecasting model from the set of trained entrant forecasting models based on computed accuracy evaluations performed over the set of forecasted values.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.