Prediction Method of Multiple Related Time Series Based on Generative Adversarial Networks

In multiple related time series prediction problems, the key is capturing the comprehensive influence of the temporal dependencies within each time series and the interactional dependencies between time series. At present, most time series prediction methods are difficult to capture the complex interaction between time series, which seriously affects the prediction results. In this paper, we propose a novel deep learning model Multiple Time Series Generative Adversarial Networks (MTSGAN) based on generative adversarial networks to solve this problem. MTSGAN is mainly composed of three components: interaction matrix generator, prediction generator, and time series discriminator. In our model, graph convolutional networks are used to extract interactional dependencies, and long short-term memory networks are used to extract temporal dependencies. Through the adversarial training between the generator and the discriminator, we enable the final prediction generator to generate prediction values that are very close to the true values. At last, we compare the prediction performance of the MTSGAN with other benchmarks on different datasets to prove the effectiveness of our proposed model, and we find that MTSGAN model consistently outperforms other state-of-the-art methods in the multiple related time series prediction problems.