I have 1.5 lac/ 150 K timeseries . These are divided by geo locations. I have total 32 geo locations.Customer is expecting to have minimum number of model for all the 1.5 lac forecasting. How should i cluster my time series in such scenario ?
DTW/ fastdtw are time consuming and can't be used on this data( becasue od sheer size; 37GB).Any other way to cluster time series in faster way?
I can devide series based on mean values/sd. This seems very crude way.
Can you suggest any approach to handle these many time series with few models?
