Skip to Content
Find More Like This
Return to Search


United States Patent Application

View the Complete Application at the US Patent & Trademark Office
A method and a system to perform multi-model blending are described. The method includes obtaining one or more sets of predictions of historical conditions, the historical conditions corresponding with a time T that is historical in reference to current time, and the one or more sets of predictions of the historical conditions being output by one or more models. The method also includes obtaining actual historical conditions, the actual historical conditions being measured conditions at the time T, assembling a training data set including designating the two or more set of predictions of historical conditions as predictor variables and the actual historical conditions as response variables, and training a machine learning algorithm based on the training data set. The method further includes obtaining a blended model based on the machine learning algorithm.
Hamann, Hendrik F. (Yorktown Heights, NY), Hwang, Youngdeok (White Plains, NY), van Kessel, Theodore G. (Millbrook, NY), Khabibrakhmanov, Ildar K. (Syosset, NY), Lu, Siyuan (Yorktown Heights, NY), Muralidhar, Ramachandran (Mahopac, NY)
International Business Machines Corporation (Armonk NY)
14/ 291,720
May 30, 2014
FEDERAL RESEARCH STATEMENT [0001] This invention was made with Government support under DE-EE0006017 awarded by the Department of Energy. The Government has certain rights to this invention.