Currently, one of the most popular advanced analytics area is time series analysis. Stored data of measuring instruments, detectors of various kinds can serve as examples of generating this kind of data.
There are quite a few integrated platforms proposals on the market for building deep learning models. In this situation, the H2O platform (framework) is a unique offer, due to its free, comprehensive, low entry threshold and scalability. Particular interest in the framework is also dictated by the fact that the developers have provided the opportunity to access the platform algorithms in R and Python using libraries, as well as the availability of the Sparkling Water application for Apache Spark. In the KNIME Analytics Platform 4.X, the KNIME Labs - Deep Learning node group has well-tuned nodes that can invoke the corresponding H2O algorithms. Currently, not all H2O algorithms have been implemented yet, but the KNIME development process allows us to expect that everything remaining will be implemented soon. The article provides general information, as well as an example of using the platform for the task of time series forecasting. The order of the functions in the code, the basic settings, as well as the call features that occur when working on a single PC while working in R are shown. The process of interaction with the web interface and the implementation of functions in the statistical programming language R is described. The use of simulation results, namely, relative importance, is demonstrated. predictors in H2O to simplify the data set and increase the rate of convergence of the algorithm.