I am doing a time series prediction model, using TCN and LSTM. I splited my data into 3 parts, train, vail and test.I only let the train data do shuffle after splited. Then I can obtain a better result than did not do shuffle. My data includes date information, the format is yyyy/mm/dd hh:mm:ss.
I really want to know the reason.
New contributor
Ackerman is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.