arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.07657q-fin.CPcs.LG
收藏

期权定价中的机器学习:网络架构的实证研究

Machine learning for option pricing: an empirical investigation of network architectures

Delft Institute of Applied Mathematics, TU Delft(代尔夫特应用数学研究所,代尔夫特理工大学);Institute of Applied and Computational Mathematics, FORTH(应用与计算数学研究所,希腊国家科研院);Department of Mathematics, TU Munich(数学系,慕尼黑工业大学)

Serena Della Corte, Laurens Van Mieghem, Antonis Papapantoleon, Jonas Papazoglou-Hennig

AI总结:

本文通过实证研究比较了不同网络架构在期权定价和隐含波动率计算中的性能,发现广义高速公路网络架构在准确性与训练时间方面表现最佳。

摘要:

我们考虑了监督学习问题,即学习期权价格或隐含波动率,给定适当的输入数据(模型参数)和相应的输出数据(期权价格或隐含波动率)。文献中大多数文章考虑使用(普通)前馈神经网络架构,以连接用于学习输入到输出函数映射的神经元。在本文中,受图像分类方法和最近在PDEs中的机器学习方法进展的启发,我们实证地研究了网络架构的选择如何影响机器学习算法的准确性和训练时间。我们发现,在考虑均方误差和训练时间作为标准的情况下,广义高速公路网络架构在Black-Scholes和Heston期权定价问题中表现最佳。在考虑转换的隐含波动率问题时,一种简化的DGM变体在测试的架构中实现了最低的误差。我们还进行了容量标准化的比较,以确保完整性,其中所有架构均以相同数量的参数进行评估。最后,在隐含波动率问题中,我们还加入了使用真实市场数据的实验。

英文摘要:

We consider the supervised learning problem of learning the price of an option or the implied volatility given appropriate input data (model parameters) and corresponding output data (option prices or implied volatilities). The majority of articles in this literature considers a (plain) feed forward neural network architecture in order to connect the neurons used for learning the function mapping inputs to outputs. In this article, motivated by methods in image classification and recent advances in machine learning methods for PDEs, we investigate empirically whether and how the choice of network architecture affects the accuracy and training time of a machine learning algorithm. We find that the generalized highway network architecture achieves the best performance, when considering the mean squared error and the training time as criteria, within the considered parameter budgets for the Black-Scholes and Heston option pricing problems. Considering the transformed implied volatility problem, a simplified DGM variant achieves the lowest error among the tested architectures. We also carry out a capacity-normalised comparison for completeness, where all architectures are evaluated with an equal number of parameters. Finally, for the implied volatility problem, we additionally include experiments using real market data.

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。

↑