arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1910.09504q-fin.STstat.ML
收藏

CorrGAN:使用生成对抗网络采样现实金融相关矩阵

CorrGAN: Sampling Realistic Financial Correlation Matrices Using Generative Adversarial Networks

Gautier Marti

摘要:

我们提出了一种新的方法来采样现实的金融相关矩阵。这种方法基于生成对抗网络。实验表明,生成式对抗网络能够恢复大多数已知的关于资产收益估计的经验相关矩阵的程式化事实。这是第一次在文献中记录这样的结果。实际的金融应用范围从交易策略增强到风险和投资组合压力测试。这样的生成模型也可以通过允许陈述的可证伪性和经验方法的更客观比较,帮助经验金融学更深入地融入科学。

英文摘要:

We propose a novel approach for sampling realistic financial correlation matrices. This approach is based on generative adversarial networks. Experiments demonstrate that generative adversarial networks are able to recover most of the known stylized facts about empirical correlation matrices estimated on asset returns. This is the first time such results are documented in the literature. Practical financial applications range from trading strategies enhancement to risk and portfolio stress testing. Such generative models can also help ground empirical finance deeper into science by allowing for falsifiability of statements and more objective comparison of empirical methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑