cs-net: structural approach to time-series forecasting for high-dimensional feature space data with limited observations
It addresses a domain-specific problem for researchers and practitioners dealing with high-dimensional time-series data, offering a solution to performance limitations in existing deep-learning methods.
The paper tackles high-dimensional multivariate time-series forecasting with limited observations by proposing a flexible data feature extraction technique, achieving 1st and 2nd place in the NSF ATD 2022 Challenge on the GDELT Dataset.
In recent years, deep-learning-based approaches have been introduced to solving time-series forecasting-related problems. These novel methods have demonstrated impressive performance in univariate and low-dimensional multivariate time-series forecasting tasks. However, when these novel methods are used to handle high-dimensional multivariate forecasting problems, their performance is highly restricted by a practical training time and a reasonable GPU memory configuration. In this paper, inspired by a change of basis in the Hilbert space, we propose a flexible data feature extraction technique that excels in high-dimensional multivariate forecasting tasks. Our approach was originally developed for the National Science Foundation (NSF) Algorithms for Threat Detection (ATD) 2022 Challenge. Implemented using the attention mechanism and Convolutional Neural Networks (CNN) architecture, our method demonstrates great performance and compatibility. Our models trained on the GDELT Dataset finished 1st and 2nd places in the ATD sprint series and hold promise for other datasets for time series forecasting.