If You Like It, GAN It. Probabilistic Multivariate Times Series Forecast With GAN
This work addresses the need for accurate probabilistic forecasts in domains like energy and finance, though it appears incremental by building on existing GAN and deterministic model techniques.
The paper tackles multivariate time-series forecasting by introducing ProbCast, a probabilistic model using a conditional GAN framework, and a method to convert deterministic models into probabilistic ones with improved performance, achieving remarkable results on electricity consumption and exchange-rate datasets.
The contribution of this paper is two-fold. First, we present ProbCast - a novel probabilistic model for multivariate time-series forecasting. We employ a conditional GAN framework to train our model with adversarial training. Second, we propose a framework that lets us transform a deterministic model into a probabilistic one with improved performance. The motivation of the framework is to either transform existing highly accurate point forecast models to their probabilistic counterparts or to train GANs stably by selecting the architecture of GAN's component carefully and efficiently. We conduct experiments over two publicly available datasets namely electricity consumption dataset and exchange-rate dataset. The results of the experiments demonstrate the remarkable performance of our model as well as the successful application of our proposed framework.