Leveraging Image-based Generative Adversarial Networks for Time Series Generation
This work addresses the challenge of time series generation for domains requiring synthetic data, representing an incremental improvement through adaptation of existing image GAN methods.
The paper tackles the problem of generating realistic time series data by proposing a novel two-dimensional image representation called Extended Intertemporal Return Plot (XIRP), which leverages image-based generative adversarial networks (GANs) and significantly outperforms a state-of-the-art RNN-based model in predictive ability.
Generative models for images have gained significant attention in computer vision and natural language processing due to their ability to generate realistic samples from complex data distributions. To leverage the advances of image-based generative models for the time series domain, we propose a two-dimensional image representation for time series, the Extended Intertemporal Return Plot (XIRP). Our approach captures the intertemporal time series dynamics in a scale-invariant and invertible way, reducing training time and improving sample quality. We benchmark synthetic XIRPs obtained by an off-the-shelf Wasserstein GAN with gradient penalty (WGAN-GP) to other image representations and models regarding similarity and predictive ability metrics. Our novel, validated image representation for time series consistently and significantly outperforms a state-of-the-art RNN-based generative model regarding predictive ability. Further, we introduce an improved stochastic inversion to substantially improve simulation quality regardless of the representation and provide the prospect of transfer potentials in other domains.