Oleg Sokolinskiy

Website with links to research: finquanti.com

Professor Sokolinskiy applies the most efficient quantitative methods to gain insights into complex financial problems related to derivative securities, financial risk management, and risk factors. His recent paper “Betting on Dependence in Post-Crisis Markets: Dispersion and Correlation Skew Trades" combines financial engineering, trading strategy construction, and knowledge of the market environment. Nearly a decade of research and teaching experience in financial engineering, fixed income, derivatives, and econometrics, establish broad foundations for future academic pursuits. His special interests include equity options, credit default swaps, and a variety of fixed income securities.

Extensive experience with Python (including numpy, pandas, scipy, dask) enable him to carry out fast and scalable hypothesis testing and to prototype solutions. He has developed and deployed a number of projects using supercomputers (coded in C++ and using MPI). Two of his published papers (with co-authors) utilize reinforcement learning, also referred to as dynamic stochastic programming or AI. Interest in deep learning and knowledge of Keras and TensorFlow (via Python API) allow him to develop machine learning FinTech applications.