About me

I am a quantitative trader with experience in credit default swaps, corporate bonds, equities and crypto futures markets. Currently working at ADIA in Abu Dhabi. Before joining ADIA, I worked for hedge funds in Hong Kong, London, and Paris (reverse chronological order). I am sort of specialized in build-outs, having participated only in greenfield projects (either brand new hedge fund or new fund within an existing asset manager). I have a keen eye for building teams with a diversified set of skills (from infrastructure, datafeeds and databases, alpha research and portfolio construction to execution).

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:

• Hong Kong Machine Learning Meetup
• Archives of the previous meetups: hkml.ai

I’m also starting a similar Meetup in Abu Dhabi:

• Abu Dhabi Machine Learning Meetup
• Archives of the previous meetups: adml.ai

Any views expressed here are unrelated to my current and past employers or what I do for them.