Option Pricing Based on the Residual Neural Network

Lirong Gan () and Wei-han Liu ()
Additional contact information
Lirong Gan: Guangdong University of Finance
Wei-han Liu: Southern University of Science and Technology

Computational Economics, 2024, vol. 63, issue 4, No 2, 1327-1347

Abstract: Abstract We employ an innovative deep learning method to price options quickly and accurately. Specifically, we construct the Residual Neural Network model (ResNet) by two different basic residual blocks with three one-dimensional convolution layers and a shortcut. This model is a generalized option pricing method, and it can be used to approximate the option pricing formula without any assumptions. Besides, the model also can be easily extended to the deep ResNet model to achieve higher prediction accuracy. Comprehensive numerical experiments show that the deep ResNet model has excellent performance in the pricing of 50ETF options in the Chinese market, and the prediction accuracy of our model is higher than that of commonly used deep learning models, including deep neural network (DNN) and fully convolutional networks (FCN).

Keywords: Option pricing; ResNet; Machine learning; Deep network (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10614-023-10413-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:kap:compec:v:63:y:2024:i:4:d:10.1007_s10614-023-10413-3

Ordering information: This journal article can be ordered from
http://www.springer. ... ry/journal/10614/PS2

DOI: 10.1007/s10614-023-10413-3

Access Statistics for this article

Computational Economics is currently edited by Hans Amman

More articles in Computational Economics from Springer, Society for Computational Economics Contact information at EDIRC.
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().