{"title":"使用特征核的 MMD 训练金融时间序列生成模型","authors":"Lu Chung I, Julian Sester","doi":"arxiv-2407.19848","DOIUrl":null,"url":null,"abstract":"Generating synthetic financial time series data that accurately reflects\nreal-world market dynamics holds tremendous potential for various applications,\nincluding portfolio optimization, risk management, and large scale machine\nlearning. We present an approach for training generative models for financial\ntime series using the maximum mean discrepancy (MMD) with a signature kernel.\nOur method leverages the expressive power of the signature transform to capture\nthe complex dependencies and temporal structures inherent in financial data. We\nemploy a moving average model to model the variance of the noise input,\nenhancing the model's ability to reproduce stylized facts such as volatility\nclustering. Through empirical experiments on S&P 500 index data, we demonstrate\nthat our model effectively captures key characteristics of financial time\nseries and outperforms a comparable GAN-based approach. In addition, we explore\nthe application of the synthetic data generated to train a reinforcement\nlearning agent for portfolio management, achieving promising results. Finally,\nwe propose a method to add robustness to the generative model by tweaking the\nnoise input so that the generated sequences can be adjusted to different market\nenvironments with minimal data.","PeriodicalId":501084,"journal":{"name":"arXiv - QuantFin - Mathematical Finance","volume":"21 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Generative model for financial time series trained with MMD using a signature kernel\",\"authors\":\"Lu Chung I, Julian Sester\",\"doi\":\"arxiv-2407.19848\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Generating synthetic financial time series data that accurately reflects\\nreal-world market dynamics holds tremendous potential for various applications,\\nincluding portfolio optimization, risk management, and large scale machine\\nlearning. We present an approach for training generative models for financial\\ntime series using the maximum mean discrepancy (MMD) with a signature kernel.\\nOur method leverages the expressive power of the signature transform to capture\\nthe complex dependencies and temporal structures inherent in financial data. We\\nemploy a moving average model to model the variance of the noise input,\\nenhancing the model's ability to reproduce stylized facts such as volatility\\nclustering. Through empirical experiments on S&P 500 index data, we demonstrate\\nthat our model effectively captures key characteristics of financial time\\nseries and outperforms a comparable GAN-based approach. In addition, we explore\\nthe application of the synthetic data generated to train a reinforcement\\nlearning agent for portfolio management, achieving promising results. Finally,\\nwe propose a method to add robustness to the generative model by tweaking the\\nnoise input so that the generated sequences can be adjusted to different market\\nenvironments with minimal data.\",\"PeriodicalId\":501084,\"journal\":{\"name\":\"arXiv - QuantFin - Mathematical Finance\",\"volume\":\"21 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuantFin - Mathematical Finance\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2407.19848\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuantFin - Mathematical Finance","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2407.19848","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
生成能准确反映现实世界市场动态的合成金融时间序列数据,对于包括投资组合优化、风险管理和大规模机器学习在内的各种应用具有巨大的潜力。我们的方法利用签名变换的表现力来捕捉金融数据中固有的复杂依赖关系和时间结构。我们采用移动平均模型对噪声输入的方差进行建模,从而增强了模型再现诸如波动集群等风格化事实的能力。通过对标准普尔 500 指数数据的实证实验,我们证明我们的模型能有效捕捉金融时间序列的关键特征,并优于基于 GAN 的同类方法。此外,我们还探索了如何将生成的合成数据用于训练投资组合管理的强化学习代理,并取得了可喜的成果。最后,我们提出了一种方法,通过调整噪声输入来增加生成模型的鲁棒性,这样生成的序列就能以最少的数据适应不同的市场环境。
Generative model for financial time series trained with MMD using a signature kernel
Generating synthetic financial time series data that accurately reflects
real-world market dynamics holds tremendous potential for various applications,
including portfolio optimization, risk management, and large scale machine
learning. We present an approach for training generative models for financial
time series using the maximum mean discrepancy (MMD) with a signature kernel.
Our method leverages the expressive power of the signature transform to capture
the complex dependencies and temporal structures inherent in financial data. We
employ a moving average model to model the variance of the noise input,
enhancing the model's ability to reproduce stylized facts such as volatility
clustering. Through empirical experiments on S&P 500 index data, we demonstrate
that our model effectively captures key characteristics of financial time
series and outperforms a comparable GAN-based approach. In addition, we explore
the application of the synthetic data generated to train a reinforcement
learning agent for portfolio management, achieving promising results. Finally,
we propose a method to add robustness to the generative model by tweaking the
noise input so that the generated sequences can be adjusted to different market
environments with minimal data.