A method for recovery of multidimensional time series based on the detection of behavioral patterns and the use of autoencoders

This article presents a method for recovering missing values in multidimensional time series. The method combines neural network technologies and an algorithm for searching snippets (behavioral patterns of a time series). It includes the stages of data preprocessing, recognition and reconstruction, using convolutional and recurrent neural networks. Experiments have shown high accuracy of recovery and the advantage of the method over SOTA methods.