I have a collection of time series data with data points of around 2 years of daily data. I am thinking of a way to increase the number of data points in it so that the neural network gets a better understanding of the fluctuations in the data. I am suggesting a hypothesis where I try to cluster similar time-series data following similar distribution, in order to increase the number of data points fed into the neural network. Is this a correct way to approach the problem? If so, on what basis do I combine these similar data together so that I can feed it into the neural network/model?