The article investigates the limitations of modern approaches to time series forecasting in complex dynamic and nonlinear processes whose structure may consist of heterogeneous data types. The relevance of the study is driven by the rapid growth of data volumes in information systems, their diversity, and the need to improve forecasting accuracy under conditions of non-stationarity and multifactor influence.
The constant growth of data volumes requires the development of effective methods for managing, processing, and storing information. Additionally, it is advisable to apply multimodal approaches for knowledge aggregation to extract additional knowledge. Usually, the problem of efficient processing of multimodal data is associated with high-quality data preprocessing. One of the most critical preprocessing steps is synchronizing multimodal data streams to analyze complex interactions in different data types.