Thesis Defence – Eren Akansel (MSFE)

Eren Akansel- M.Sc. Financial Engineering

Asst. Prof. Dr. Emrah Ahi – Advisor

Date: 13.05.2025

Time: 15:00

Location: Özyeğin University Altunizade Campus - Classroom ALT 101

“Forecasting The Turkish Yield Curve Using Deep Learning And Econometric Models: A Comparative Analysis”

Asst. Prof. Dr. Emrah Ahi, Özyeğin University

Asst. Prof. Dr. Levent Güntay, Özyeğin University

Asst. Prof. Dr. Rıza Ergün Arsal, İstanbul Bilgi University

Abstract:

This study aims to investigate the predictive power of time series and machine learning models, including AR, PCA-VAR, PCR, and FeedForward Neural Networks (FNN), in modeling the implied volatility surfaces of five emerging market currencies (TRY, INR, MXN, ZAR, BRL against USD). The research evaluates model performance based on the Root Mean Square Error (RMSE) metric using both the Expanding and Rolling Window methods. The findings indicate that the AR, PCA-VAR, and FNN models not constrained by fixed hyperparameters yield comparably accurate results, particularly for currencies with lower levels of volatility. The study highlights the critical importance of model selection in financial forecasting and suggests that the incorporation of macroeconomic or geopolitical factors into the models may further enhance forecasting accuracy.

 Keywords: Machine learning, Implied Volatility Surface, Time Series Forecasting, Feedforward Neural Network, Principal Component Analysis (PCA), Currency Options, Emerging Markets

Bio:       

Eren Akansel graduated from the Management Engineering Department of Istanbul Technical University in 2015. After graduating, he began his career in the economics and finance sector, and for the past three years he has been working in the Treasury department of a private bank.