Automated time series forecasting pipeline generation

US11966340B2 · kind B2 · utility

Assignee

• International Business Machines Corporation · US

Inventors

• Long Vu · Chappaqua, US
• Bei Chen · Dublin, IE
• Xuan-Hong Dang · Chappaqua, US
• Peter D. Kirchner · Garrison, US
• Syed Yousaf Shah · Yorktown Heights, US
• Dhavalkumar C. Patel · White Plains, US
• Si Er Han · Xi'an, CN
• Ji Hui Yang · Beijing, CN
• Jun Wang · Yangshuo, CN
• Jing Xu · Shanghai, CN
• Dakuo Wang · Cambridge, US
• Gregory Bramble · Larchmont, US
• Horst Cornelius Samulowitz · Armonk, US
• Saket Sathe · Mohegan Lake, US
• Wesley M. Gifford · Ridgefield, US
• Petros Zerfos · New York, US

Key dates

• Filing date: Mar 15, 2022
• Grant date: Apr 23, 2024
• Expiry date: Jul 16, 2042

Classification

• Technology area (CPC G): Physics
• CPC primary: G06F2212/604
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

To automate time series forecasting machine learning pipeline generation, a data allocation size of time series data may be determined based on one or more characteristics of a time series data set. The time series data may be allocated for use by candidate machine learning pipelines based on the data allocation size. Features for the time series data may be determined and cached by the candidate machine learning pipelines. Predictions of each of the candidate machine learning pipelines using at least the one or more features may be evaluated. A ranked list of machine learning pipelines may be automatically generated from the candidate machine learning pipelines for time series forecasting based upon evaluating predictions of each of the one or more candidate machine learning pipelines.