Neural Networks for Contingent Claim Pricing via the Galerkin Method
Neural Networks for Contingent Claim Pricing via the Galerkin Method
复制标题
通过 Galerkin 方法进行或有债权定价的神经网络
DOI：
10.1007/978-1-4757-2644-2_9
复制
发表时间：
1997
期刊：
影响因子：
--
通讯作者：
L. Landi
中科院分区：
文献类型：
--
作者：
E. Barucci;Umberto Cherubini;L. Landi
我们使用神经网络作为半非参数技术，通过伽辽金方法来近似由无套利偏微分方程定义的或有索赔价格。确定神经网络的权重以满足无套利偏微分方程。为欧洲或有债权制定了通用解决程序。神经网络的主要特点是它的权重是时变的，它们随着索赔到期时间的变化而变化。该方法已在标准布莱克和斯科尔斯框架中进行了期权定价评估。
We use Neural Networks as a Semi-NonParametric technique to approximate, by means of the Galerkin method, contingent claim prices defined by a no-arbitrage Partial Differential Equation. The Neural Networks’ weights are determined as to satisfy the no-arbitrage Partial Differential Equation. A general solution procedure is developed for European Contingent Claims. The main feature of the Neural Network is that its weights are time varying, they change as the time to expiration of the claim changes. The method has been evaluated for option pricing in the standard Black and Scholes framework.