kth.sePublications KTH
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Approximation of Option Prices with Machine Learning Methods
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Mathematics (Div.).
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Approximering av optionspriser med maskininlärningsmetoder (Swedish)
Abstract [en]

This thesis investigates the use of neural networks to estimate prices of European call options and exotic options. The dataset used in the thesis consists of historical price data for European call options written on the S&P 500 and two synthetic data sets generated from a model in which it is assumed that the underlying assets are correlated geometric Brownian motions and a Heston model. Neural networks with depths ranging from 1 to 9 layers are evaluated. The results suggest that neural networks with more than six layers can provide better out-of-sample performance compared to networks with fewer layers for the options considered.

Abstract [sv]

I den här uppsatsen används neurala nätverk för att estimera priser på europeiska köpoptioner och exotiska optioner. Det data som används består av historiska priser för europeiska köpoptioner skrivna på S&P 500 och två syntetiska datamängder genererade från en modell där de underliggande tillgångarna antas vara korrelerade geometriska brownska rörelser och en Heston-modell. Neurala nätverk med djup mellan 1 och 9 lager utvärderas. Uppsatsen drar slutsatsen att neurala nätverk med fler än sex lager kan prestera bättre än nätverk med färre vid estimering av priser för de studerade optionerna.

Place, publisher, year, edition, pages
2024. , p. 68
Series
TRITA-SCI-GRU ; 2024:434
Keywords [en]
Financial Mathematics, Quantitative Finance, Neural Networks, Machine Learning, Deep Learning, Financial derivatives, Options, Exotic options
Keywords [sv]
Finansiell matematik, Kvantitativ finans, Neurala Nätverk, Maskininlärning, Djupinlärning, Finansiella derivat, Optioner, Exotiska optioner
National Category
Other Mathematics
Identifiers
URN: urn:nbn:se:kth:diva-363935OAI: oai:DiVA.org:kth-363935DiVA, id: diva2:1961956
Subject / course
Financial Mathematics
Educational program
Master of Science - Applied and Computational Mathematics
Supervisors
Examiners
Available from: 2025-06-02 Created: 2025-05-28 Last updated: 2025-07-08Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
Mathematics (Div.)
Other Mathematics

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 865 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf