US Patent Issued to TATA CONSULTANCY SERVICES on Dec. 9 for "Encoder decoder based RNN learning for multi-step time series forecasting in presence of missing data" (Indian Inventors)

ALEXANDRIA, Va., Dec. 9 -- United States Patent no. 12,493,794, issued on Dec. 9, was assigned to TATA CONSULTANCY SERVICES Ltd. (Mumbai, India).

"Encoder decoder based RNN learning for multi-step time series forecasting in presence of missing data" was invented by Avinash Achar (Chennai, India) and Soumen Pachal (Chennai, India).

According to the abstract* released by the U.S. Patent & Trademark Office: "This disclosure relates generally to a method and system for encoder decoder based RNN learning for time series forecasting in presence of missing data. The present disclosure employs atleast one multi-layer RNN encoder and a decoder for time series forecasting. The method receives a plurality of input data comprising a sequential data t...