System and method for neural time series preprocessing

A system for preprocessing and forecasting neural time series data, the system comprising:

• at least one processor;
• and
• a memory comprising instructions which, when executed by the processor, configure the processor to:
• divide time series data to generate chunks of short time series;
• input each of the short time series to a data preprocessing neural network that includes differencing to transform non-stationary data to more stationary data and to filter noise;
• generate and output, from the data preprocessing neural network, processed time series data;
• and
• input the processed time series data to a forecasting neural network;
• wherein parameters of the data preprocessing neural network and parameters of the forecasting neural network are learned end-to-end.