We benchmark the performance of widely used long short-term memory (LSTM) models in predicting standardized implied volatility (IV) of equity options against a range of alternative time series models. We forecast option prices over the period 2018-2023 and find universal models that are trained on data pooled across all underlyings to perform the best. The highest forecasting accuracy is achieved by a bidirectional LSTM model with one hidden layer. This provides evidence outside the stock markets that using universal models with pooled data across underlyings to train neural networks significantly improves the forecasting accuracy for equity option prices. Once the machine learning model is trained, one can inexpensively use the trained models to predict option prices up to 7 years into the future.
Fritzsch, Simon, Irresberger, Felix, Weiß, Gregor. Predicting option prices from their price history via machine learning. // Review of Derivatives Research. – 2026. – DOI: 10.1007/s11147-026-09228-9. – URL: http://link.springer.com/openurl/fulltext?id=doi:10.1007/s11147-026-09228-9
Fritzsch, Simon, Irresberger, Felix, Weiß, & Gregor (2026). Predicting option prices from their price history via machine learning. Review of Derivatives Research. https://doi.org/10.1007/s11147-026-09228-9
Fritzsch, et al. “Predicting option prices from their price history via machine learning.” Review of Derivatives Research, 2026. doi:10.1007/s11147-026-09228-9.
@article{Fritzsch2026,
title = {Predicting option prices from their price history via machine learning},
author = {Fritzsch and Simon and Irresberger and Felix and Weiß and Gregor},
journal = {Review of Derivatives Research},
year = {2026},
doi = {10.1007/s11147-026-09228-9},
url = {http://link.springer.com/openurl/fulltext?id=doi:10.1007/s11147-026-09228-9}
}
The detection of vehicle insurance fraud remains a key concern since high-performance artificial intelligence (AI) models cannot be completely trusted, while rule-based methods are too rigid to encompass shifting fraud tactics. Machine...
We derive a series representation for European call prices when the terminal log-return shock follows a skew-generalized secant hyperbolic (SGSH) distribution. We use the generating function for Chebyshev polynomials of the second kind...
In a competitive green trade market, sustainability has become a critical component of modern business strategy. Manufacturers are increasingly incorporating environmental considerations, particularly carbon-emission regulations and...
This study examines how persuasive cues embedded in generative artificial intelligence-enabled e-commerce interfaces shape consumers’ flow experience and how these effects vary with consumer involvement. Drawing on the Elaboration...
This study offers a systematic literature review of cybersecurity behavior under the lens of the Protection Motivation Theory (PMT). Using the Scopus database, we extract and analyze 34 relevant articles following the approach of Paul...