My research interests include (excluding proprietary research for alpha strategies) generative adversarial networks, knowledge graphs, graph neural networks, information geometry, geometry of correlation matrices, hierarchical clustering.
My two most innovative ideas in academic research:
- using optimal transport between well-chosen copulas to define new dependence measures,
- using generative adversarial networks to generate realistic random correlation matrices (to test the robustness of strategies and portfolio construction methods with large Monte Carlo simulations).
Some research presentations I did at conferences can be found here
Some of my research has been featured in Risk.net: - In fake data, quants see a fix for backtesting - Quants turn to machine learning to unlock private data
And, in MIT The Net Advance of Physics.
I organize a monthly meetup on Machine Learning and its applications in Hong Kong:
I’m also starting a similar Meetup in Abu Dhabi:
Any views expressed here are unrelated to my current and past employers or what I do for them.