Multi-dimensional time series event prediction via convolutional neural network(s)

A computer-implemented method, comprising:

• generating, by a system operatively coupled to a processor, a first sequence of multi-dimensional time series data and a second sequence of multi-dimensional time series data from multi-dimensional time series data associated with at least two different data types generated by a data system over a consecutive period of time, wherein the first sequence and the second sequence comprise:
• dynamic data having a time dependency with one or more other data elements included in the multi-dimensional time series data and that has been modified by the system one or more times, and static data that has not been modified by the system;
• concurrently analyzing, by the system, the first sequence of multi-dimensional time series data and the second sequence of multi-dimensional time series data using a convolutional neural network system;
• generating, by the system, prediction data that comprises a predicted event associated with the multi-dimensional time series data based on the analyzing the data matrix using the convolutional neural network system that outputs features to a classifier to generate a prediction result associated with a prediction of an event associated with the multi-dimensional time series data;
• and
• determining and providing, by the system, as feedback based on the prediction result information to tune one or more parameters for the convolutional neural network system based on characteristics of the multi-dimensional time series data, wherein the one or more parameters comprise at least one of a number of hidden layers for the convolutional neural network, a dropout rate for the convolutional neural network or a type of filter for the convolutional neural network.