Introduction

I am currently working as a research assistant at Rotman FinHub at University of Toronto. My research focus on financial applications of machine learning techniques. To begin with, we employ NLP methodologies to analyze news text and earnings announcements. This approach enables us to quantify market uncertainty and explain post-announcement returns. Secondly, we leverage Variational Auto-Encoders to model the evolutions of implied volatility surfaces and asset prices.

Publications

• MASc Thesis, “Navigating Market Uncertainty: News Narrative Analysis and Synthetic Volatility Modeling”.
  • Supervisor: Andreas Veneris
  • Committee: John Hull, Charles Martineau
• Jacky Chen, John Hull, Zissis Poulos, Haris Rasul, Andreas Veneris, Yuntao Wu, “A Variational Autoencoder Approach to Conditional Generation of Possible Future Volatility Surfaces”. [SSRN]
• Kevin Benson, John Hull, Yoshio Nozawa, Zissis Poulos, Vasily Strela, Yuntao Wu, “Forecasting Using Text-Based Uncertainty Measures”. [SSRN]
• Charles Martineau, Zissis Poulos, Yuntao Wu, Cameron Thompson, Maryam Haghighi, Jun Yuan, John Hull, “Narrative Monetary Policy Uncertainty,” in Proceedings of the Irving Fisher Committee Satellite Seminar held at the ISI 64th World Statistics Congress, co-organised with the Bank of Canada, Ottawa, Canada, 15 July 2023. [GitHub] [SSRN] [IFC Bulletin] [dataset visualization]
• Charles Martineau, Zissis Poulos, Bowen Wu, Yuntao Wu, “How important is soft information to price efficiency to following earning announcements” (in draft) [GitHub]

Services

• ProQuest TDM Studio Case Study: Harnessing Machine Learning with News Data for Economic Insights (2023, published in 2024) [Final Report]
• IEEE Transactions on Network and Service Management: External Reviewer (2023-2024)