Applied Neural Network Methods for Option Pricing

Thesis title: Applied Neural Network Methods for Option Pricing
Author: Boiko, Andre
Thesis type: Diploma thesis
Supervisor: Čabla, Adam
Opponents: Danko, Jakub
Thesis language: English
Abstract:
This thesis investigates whether neural networks can be used for option pricing while still respecting basic financial rules. It compares four models: two feed-forward neural networks and two physics-informed neural networks using synthetic option prices generated with the Heston model and the COS method. The models are evaluated not only by pricing accuracy, but also by no-arbitrage checks such as price bounds, monotonicity, convexity, maturity consistency, and put-call parity. The results show that the call-only FFNN gives the most accurate prices, while the hard-bounds PINN successfully removes price-bound violations. At the same time, convexity violations remain a challenge, indicating that accurate predictions do not automatically lead to financially consistent option surfaces.
Keywords: option pricing; feed-forward neural networks; COS method; physics-informed neural networks; no-arbitrage; Heston model
Thesis title: Applied Neural Network Methods for Option Pricing
Author: Boiko, Andre
Thesis type: Diplomová práce
Supervisor: Čabla, Adam
Opponents: Danko, Jakub
Thesis language: English
Abstract:
This thesis investigates whether neural networks can be used for option pricing while still respecting basic financial rules. It compares four models: two feed-forward neural networks and two physics-informed neural networks using synthetic option prices generated with the Heston model and the COS method. The models are evaluated not only by pricing accuracy, but also by no-arbitrage checks such as price bounds, monotonicity, convexity, maturity consistency, and put-call parity. The results show that the call-only FFNN gives the most accurate prices, while the hard-bounds PINN successfully removes price-bound violations. At the same time, convexity violations remain a challenge, indicating that accurate predictions do not automatically lead to financially consistent option surfaces.
Keywords: Heston model; no-arbitrage; option pricing; physics-informed neural networks; eed-forward neural networks; COS method

Information about study

Study programme: Economic Data Analysis/Data Analysis and Modeling
Type of study programme: Magisterský studijní program
Assigned degree: Ing.
Institutions assigning academic degree: Vysoká škola ekonomická v Praze
Faculty: Faculty of Informatics and Statistics
Department: Department of Statistics and Probability

Information on submission and defense

Date of assignment: 27. 10. 2025
Date of submission: 21. 6. 2026
Date of defense: 19. 8. 2026
Identifier in the InSIS system: https://insis.vse.cz/zp/94269/podrobnosti

Files for download

    Last update: