We focus on usefulness of machine learning techniques in economics and finance. At its core, one may perceive machine learning as a general statistical analysis that economists can use to capture complex relationships that are hidden when using simple linear methods. The ability of machine learning techniques to find relationships in data seems well-suited for financial applications. In a paper [1], we evaluate the economic gains of using deep learning methods for the construction of optimal portfolios.

Papers/Working Papers

1. Deep Learning, Predictability, and Optimal Portfolio Returns. J Barunik, M. Babiak. preprint draft (Sept 2020).
2. Combining high frequency data with non-linear models for forecasting energy market volatility. J. Barunik, T. Krehlik. Expert Systems With Applications. 55(1), 2016, p. 222-242.
3. Forecasting the term structure of crude oil futures prices with neural networks. J. Barunik, B. Malinska. Applied Energy. 164(1), 2016, p. 366-379.

Work in Progress

• Deep Reinforcement Learning for Dynamic Decision Making with Quantile Preferences (J.Barunik and L.Vacha)
• Asset Pricing with Quantile Machine Learning (J.Barunik, A.Galvao and M.Hronec)
• Dynamic density forecasting using machine learning (J.Barunik and L.Hanus)