About Datapred

DATAPRED IS THE MOST COMPREHENSIVE FRAMEWORK FOR APPLYING MACHINE LEARNING TO TIME SERIES. Datapred streamlines everything that is specific about time series modeling at every stage of the ML pipeline - preprocessing, modeling and post-processing. Notable features include: sequentialization of feature extraction, prevention of future leakage, sequentialization of batch algorithms, sequential aggregation, definition of custom cost functions, backtest automation... Use Datapred like SageMaker: from a Jupyter Notebook, with the ML library of your choice.