Machine Learning for Continuous-Time Finance

被引:0
|
作者
Duarte, Victor [1 ]
Duarte, Diogo [2 ]
Silva, Dejanir H. [3 ]
机构
[1] Univ Illinois, Champaign, IL 61820 USA
[2] Florida Int Univ, Miami, FL USA
[3] Purdue Univ, Purdue, IN USA
来源
REVIEW OF FINANCIAL STUDIES | 2024年 / 37卷 / 11期
关键词
G11; G12; G32; AMERICAN OPTIONS; RETURNS; MODELS; CONSUMPTION; MACRO; GAME; GO;
D O I
10.1093/rfs/hhae043
中图分类号
F8 [财政、金融];
学科分类号
0202 ;
摘要
We develop an algorithm for solving a large class of nonlinear high-dimensional continuous-time models in finance. We approximate value and policy functions using deep learning and show that a combination of automatic differentiation and Ito's lemma allows for the computation of exact expectations, resulting in a negligible computational cost that is independent of the number of state variables. We illustrate the applicability of our method to problems in asset pricing, corporate finance, and portfolio choice and show that the ability to solve high-dimensional problems allows us to derive new economic insights.
引用
收藏
页码:3217 / 3271
页数:55
相关论文
共 50 条