PhD Oral Exam - Parisa Foroutan, Supply Chain and Business Technology Management

When studying for a doctoral degree (PhD), candidates submit a thesis that provides a critical review of the current state of knowledge of the thesis subject as well as the student’s own contributions to the subject. The distinguishing criterion of doctoral graduate research is a significant and original contribution to knowledge.

Once accepted, the candidate presents the thesis orally. This oral exam is open to the public.

Abstract

Understanding the dynamics of financial markets specially during financial crises and being able to forecast these markets are crucial for policymakers and investors. This dissertation aims to explore the dynamics of Crude oil, Gold, Silver, and Cryptocurrency markets from various perspectives.

The first topic of the dissertation involves comparing the dynamics of cryptocurrencies, crude oil, and gold markets before and during the COVID-19 pandemic. This topic comprises two research studies: First, we investigated the effect of COVID-19 pandemic on the return-volume and return-volatility relationships of crude oil, gold, and ten-most traded cryptocurrency markets. The findings of the first study enable policymakers and investors to better react to the dynamics of digital currencies, and commodity markets during financial crisis. Then, using statistical and econometrics methods, we examined the interactions between these markets before and after the COVID-19 pandemic and investigated whether gold or crude oil can play a safe-haven role for cryptocurrency markets during the pandemic crisis. This study assists hedge fund managers or individual investors to adapt their risk exposure to crude oil, gold, and cryptocurrency markets during the financial crises.

For the second topic, several deep learning, machine learning, and hybrid models are adapted to improve the forecasting of crude oil, gold, and silver markets. For this purpose, I implemented sixteen different deep learning and machine learning models on historical price data and compared the prediction performance of these models across four different input sequence lengths to find the optimal settings in forecasting each market. The findings of this study assist investors, policymakers, and governmental agencies to effectively anticipate market trends and make informed timely decisions regarding crude oil, gold, and silver markets.

Lastly, I propose three graph-based neural networks models to predict the direction of price movements in crude oil, gold, and silver markets using a comprehensive set of features such as historical price data, global macroeconomic factors, supply and demand-related factors, other financial markets, and technical indicators. The proposed graph-based models consider the relationship among various factors that can affect the direction of price movements in crude oil and precious metal markets and can be considered as a feature extraction module for predicting the future trend of crude oil, gold, and silver markets.