Amazon Technologies, Inc.

Spyridon Garyfallos

Thomas Boyd Johnston

Wei Niu

Jing Zhang

Vinay Kale

Correcting time series predictions for seasonality using trends may be performed. An initial time series prediction for a period of time using a machine learning model trained on a time series may be made. Data of the time series from more than an analysis time period prior to the period of time may be obtained. The time series prediction and the obtained data of the time series may be decomposed in respective components including a trend component. The respective trend component of the obtained data may evaluated to determine whether a trend replacement criteria is satisfied. The respective trend component of the time series prediction may be replaced with a portion corresponding to the period of time in a prior analysis time period from the respective component of the obtained data of the time series to correct the time series prediction for seasonality.

Growing community of inventors

Seattle, WA, United States of America

Spyridon Garyfallos