We introduce the decision-aware time-series conditional generative adversarial network (DAT-CGAN) as a method for time-series generation. The framework adopts a multi-Wasserstein loss on structured decision-related quantities, capturing the heterogeneity of decision-related data and providing new effectiveness in supporting the decision processes of end users. We improve sample efficiency through an overlapped block-sampling method, and provide a theoretical characterization of the generalization properties of DAT-CGAN. The framework is demonstrated on financial time series for a multi-time-step portfolio choice problem. We demonstrate better generative quality in regard to underlying data and different decision-related quantities than strong, GAN-based baselines.
@article{arxiv.2009.12682,
title = {Decision-Aware Conditional GANs for Time Series Data},
author = {He Sun and Zhun Deng and Hui Chen and David C. Parkes},
journal= {arXiv preprint arXiv:2009.12682},
year = {2023}
}