Usage of the machine learning to organize time series and find anomalies

Abstract

The subject of the study is the process of collecting, preparing, and searching for anomalies on data from heterogeneous sources. Economic information is naturally heterogeneous and semi-structured or unstructured. This makes pre-processing of input dynamic data an important prerequisite for the detection of significant patterns and knowledge in the subject area, so the topic of research is relevant. Pre-processing of data is several unique problems that have led to the emergence of various algorithms and heuristic methods for solving such pre-processing problems as merging and cleaning and identifying variables. In this work, an algorithm for preprocessing and searching for anomalies using LSTM is formulated, which allows you to consolidate into a single database and structure information by time series from different sources, as well as search for anomalies in an automated mode. A key modification of the preprocessing method proposed by the authors is the technology of automated data integration. The technology proposed by the authors involves the joint use of methods for building a fuzzy time series and machine lexical matching on a thesaurus network, as well as the use of a universal database built using the MIVAR concept. The preprocessing algorithm forms a single data model with the possibility of transforming the periodicity and semantics of the data set and integrating into a single information bank data that can come from various sources.