Στοχαστικά μοντέλα αποτίμησης συμβολαίων μελλοντικής εκπλήρωσης πετρελαίου
View/
Keywords
Συμβόλαια Μελλοντικής Εκπλήρωσης (ΣΜΕ) ; Τιμολόγηση Futures ; Αργό πετρέλαιο ; Στοχαστικά μοντέλα ; Γεωμετρική κίνηση Brown (GBM) ; Διαδικασία Ornstein-Uhlenbeck (OU) ; Διαδικασία Cox-Ingersoll-Ross (CIR) ; Mean-reversion ; Εκτίμηση παραμέτρων ; Προβλεπτική ικανότηταAbstract
This thesis examines the pricing of crude oil futures contracts using stochastic models proposed in the existing literature. The study focuses on the presentation, estimation, and comparison of four stochastic models, distinguished by their theoretical features and the stochastic processes they follow. These models are based on fundamental stochastic processes, including the geometric Brownian motion, the Ornstein-Uhlenbeck process, and the modified CIR process, which enable the description of the behavior of the underlying asset's price.
The aim of the thesis is to estimate and compare the accuracy and predictive power of these models, taking into account the unique characteristics of the oil market, such as the stochastic nature of prices, high volatility, and the mean-reverting behavior of long-term price levels. The methodology combines a theoretical analysis of the mathematical foundations of each model, empirical parameter estimation using the nonlinear least squares method, and an evaluation of the models using real market data for WTI crude oil. The empirical study focuses on both in-sample and out-of-sample performance and examines the behavior of the models across different time-to-maturity horizons for futures contracts.
The findings suggest that more sophisticated models, which incorporate mean-reverting dynamics and nonlinear diffusion terms, demonstrate clear superiority in futures pricing. Specifically, these models achieve higher accuracy in short-term contracts and exhibit exceptional performance in long-term contracts. In contrast, simpler approaches, such as the geometric Brownian motion, show limitations, particularly in periods of high volatility or for longer time horizons.
This thesis highlights that the selection of the appropriate stochastic model not only improves pricing accuracy, but also enhances risk management in oil derivatives markets. The results contribute to a deeper understanding of the mechanisms driving futures prices and provide valuable tools for investors, risk managers, and policymakers.
Postgraduate Studies Programme
Χρηματοοικονομική και Τραπεζική με ειδίκευση στη Χρηματοοικονομική και Τραπεζική ΔιοικητικήDepartment
Σχολή Χρηματοοικονομικής και Στατιστικής. Τμήμα Χρηματοοικονομικής και Τραπεζικής ΔιοικητικήςNumber of pages
81Language
Greek
Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα