Decision-Aware Conditional GANs for Time Series Data
This addresses the need for decision-aware time-series generation in domains like finance, though it appears incremental as it builds on existing GAN methods with specific enhancements.
The paper tackles the problem of generating time series data that supports decision processes by introducing DAT-CGAN, which uses a multi-Wasserstein loss on decision-related quantities and overlapped block-sampling for efficiency, and demonstrates better generative quality than GAN-based baselines in financial portfolio choice.
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.