Decision-Aware Conditional GANs for Time Series Data
Name
3604237.3626855.pdf
Size
1.18 MB
Format
Adobe PDF
Checksum (MD5)
70207f6ecd3c2c11df1ebe072f27124a
Author(s)
Sun, He
Deng, Zhun
Chen, Hui
Parkes, David
Date Issued
November 27, 2023
Publisher
ACM|4th ACM International Conference on AI in Finance
Citation
Sun, He, Deng, Zhun, Chen, Hui and Parkes, David. 2023. "Decision-Aware Conditional GANs for Time Series Data."
Version
Final published version
Abstract
We introduce the decision-aware time-series conditional generative adversarial network (DAT-CGAN), a method for the generation of time-series data that is designed to support decision-making. The framework adopts a multi-Wasserstein loss on decision-related quantities and an overlapped block-sampling approach for sample
efficiency. We characterize the generalization properties of DAT-CGAN and in application to a multi-period portfolio choice problem and financial time series data, we demonstrate better training stability and generative quality in regard to both raw data and decision-related quantities than strong GAN-based baselines.
MIT Department
Sloan School of Management
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3604237.3626855
