arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.05810q-fin.PRcs.LG
收藏

用于各种不同过程下的Vanilla/Exotic期权定价/校准的有监督深度神经网络(DNN)

Supervised Deep Neural Networks (DNNs) for Pricing/Calibration of Vanilla/Exotic Options Under Various Different Processes

Shanghai Advanced Institute of Finance(上海高级金融学院);Orient Securities(东方证券);Cubist Systematic Strategies(库比斯特系统策略公司)

Ali Hirsa, Tugce Karatas, Amir Oskoui

摘要:

我们应用有监督的深度神经网络(DNN)对具有和不具有随机波动率的扩散和纯跳跃过程下的普通期权和奇异期权进行定价和校准。我们训练我们的神经网络模型在不同的层数,每层的神经元,和各种不同的激活函数,以找到哪些组合更好地工作经验。对于训练,我们考虑各种不同的损失函数和优化例程。我们证明,与常用的期权定价方法相比,深度神经网络以指数方式加快了期权定价,从而使校准和参数估计超快。

英文摘要:

We apply supervised deep neural networks (DNNs) for pricing and calibration of both vanilla and exotic options under both diffusion and pure jump processes with and without stochastic volatility. We train our neural network models under different number of layers, neurons per layer, and various different activation functions in order to find which combinations work better empirically. For training, we consider various different loss functions and optimization routines. We demonstrate that deep neural networks exponentially expedite option pricing compared to commonly used option pricing methods which consequently make calibration and parameter estimation super fast.

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。

↑