Towards Accurate Option Price Prediction with Improved Machine Learning Models

Trivedi, Awadhesh Premshankar (2024) Towards Accurate Option Price Prediction with Improved Machine Learning Models. Masters thesis, Dublin, National College of Ireland.

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

Abstract

The pricing of derivatives is quite complex in the derivatives market and especially when the statistical data is voluminous and the dimensionality is high, the Black-Scholes formula often provides substandard results. Several Machine Learning (ML) approaches have been developed due to help facilitate the higher predictive capability and adaptation according to the changes of the market. This paper focuses on the use of several techniques in option pricing using ML and compares them with standard models. Of all the models compared, CatBoost was identified to outperform the others because it is capable of handling non-linear features as well as categorical data. Using regulatory functions, CatBoost provided the highest accuracy and proved its ability to model complex dependencies in the analyzed financial data. Other models that we used in the analysis are LSTM networks, Random Forest, and XGBoost. These models were selected for their applicability in imaging dynamic behaviors of stock markets, that entail elimination of market risks and constant fluctuations. Other techniques, including bagging and boosting, were also used to strengthen the stability in the prediction. The results strengthen the evidence that using various ML techniques, especially CatBoost, enhances the option pricing equations while offering a suitable framework to address real and virtual financial market environments. Each of these frameworks forms a single family of approaches that narrower the gap between the more classical analytical models and the data-driven application of today’s modern world refined probabilities and improved risk management within the derivatives market domain.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Yaqoob, Abid UNSPECIFIED
Uncontrolled Keywords:	Black Lock – Scholes Model; Option Valuation; Derivatives; Linear regression; Random Forest Algorithm; XGBoost; Catboost; LSTM
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > Economics Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	05 Sep 2025 13:22
Last Modified:	05 Sep 2025 13:23
URI:	https://norma.ncirl.ie/id/eprint/8828

Actions (login required)

View Item