Modeling Implied Volatility Using Out-of-The-Money Options: A Machine Learning Approach for AAPL

Gomez Garzon, Laura Natalia (2025) Modeling Implied Volatility Using Out-of-The-Money Options: A Machine Learning Approach for AAPL. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (881kB) | Preview

Abstract

This research investigates whether OTM call and put options alone can accurately model Apple Inc. (AAPL) implied volatility surface, and compares predictive accuracy between several machine learning, deep learning architectures, and classic linear models. With a filtered sample of 3,407 AAPL OTM options and an optimal set of features, the research trains multiple models, including machine learning and linear regressors. Gradient Boosting, after tuning hyperparameters, is the best-performing model with an R² score of 0.9959, significantly outperforming linear baselines. Explainability methods like SHAP and LIME reveal moneyness to be the strongest predictor. The findings indicate that OTM options alone are not only sufficient but also optimal for IV modeling in this case. The work contributes to the existing literature demonstrating the effectiveness of tree-based models and proposes interpretable measures to explain the tail-risk dynamics of equity options.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Byrne, Brian UNSPECIFIED
Subjects:	H Social Sciences > HG Finance H Social Sciences > HG Finance > Fintech T Technology > T Technology (General) > Information Technology > Fintech Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in FinTech
Depositing User:	Ciara O'Brien
Date Deposited:	20 Aug 2026 10:52
Last Modified:	20 Aug 2026 10:52
URI:	https://norma.ncirl.ie/id/eprint/9571

Actions (login required)

View Item