English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We consider the supervised learning problem of learning the price of anoption or the implied volatility given appropriate input data (modelparameters) and corresponding output data (option prices or impliedvolatilities). The majority of articles in this literature considers a (plain)feed forward neural network architecture in order to connect the neurons usedfor learning the function mapping inputs to outputs. In this article, motivatedby methods in image classification and recent advances in machine learningmethods for PDEs, we investigate empirically whether and how the choice ofnetwork architecture affects the accuracy and training time of a machinelearning algorithm. We find that for option pricing problems, where we focus onthe Black--Scholes and the Heston model, the generalized highway networkarchitecture outperforms all other variants, when considering the mean squarederror and the training time as criteria. Moreover, for the computation of theimplied volatility, after a necessary transformation, a variant of the DGMarchitecture outperforms all other variants, when considering again the meansquared error and the training time as criteria.

Machine learning for option pricing: an empirical investigation of network architectures