Black-Scholes模型下美式期权定价的神经网络算法  

Neural Network Algorithm for American Option Pricing under Black-Scholes Model

作　　者：宋海明[1] 侯頔 SONG Haiming;HOU Di(College of Mathematics,Jilin University,Changchun 130012,China)

机构地区：[1]吉林大学数学学院,长春130012

出　　处：《吉林大学学报（理学版）》2021年第5期1089-1092,共4页Journal of Jilin University:Science Edition

基　　金：吉林省自然科学基金(批准号:20190103029JH,20200201269JC);吉林省教育厅科学研究项目(批准号:JJKH20211031KJ).

摘　　要：考虑Black-Scholes模型下的美式看跌期权定价问题.首先,基于Black-Scholes模型,设计一种针对该模型的神经网络算法,并给出美式期权价格的数值近似;其次,通过与传统的二叉树方法对比,证明该算法的有效性.We considered the American put option pricing problem under Black-Scholes model.Firstly,based on the Black-Scholes model,we designed a neural network algorithm for the model,and gave the numerical approximation of the American option price.Secondly,the effectiveness of the algorithm was proved by comparing with the traditional binomial tree method.

关 键 词：BLACK-SCHOLES模型 美式看跌期权 深度神经网络 

分 类 号：O241.8[理学—计算数学]