Dr. Nam H. Le

Background

I am a researcher working on complex adaptive systems — systems made of many interacting parts whose collective behaviour cannot be read off any single part. My doctorate is in computer science, with research spanning evolutionary computation, artificial life, and non-linear dynamics.

I taught Chaos Theory in Computational Finance as a master's course at the University of Southampton. The course materials are public, and they are a fair guide to how I think about markets: the repository is on GitHub.

BunnyQuant came out of that work. It exists because the tools that treat a market as a complex system rather than a chart pattern have historically been locked inside institutions, and there was no good reason for that to stay true.

Research areas

Evolutionary computation

Genetic programming, optimisation under uncertainty, and how systems adapt when the objective itself keeps moving.

Artificial life and collective intelligence

Emergent behaviour, multi-agent systems, swarm dynamics — how coherent structure arises from many independent actors with no coordinator.

Deep reinforcement learning

Control under sparse, delayed feedback in high-dimensional state spaces — the same shape of problem as deciding a trade.

Chaos and complexity in finance

Non-linear dynamics, regime detection, and the hierarchical structure that makes a market look different at every scale.

The idea behind the platform

A market is not a signal to be smoothed. It is millions of participants continuously adapting to each other, which produces the one property that matters most here: the same structure repeats at every scale. What is meaningless noise on a one-minute chart is genuine structure on a daily one, and a pattern that looks decisive on its own often dissolves once you look at the timeframe above it.

That is why the platform is built around scale rather than around indicators. It asks what kind of market this is right now, whether the timeframes agree with one another, how wide the range of plausible outcomes is, and what the bad outcomes actually cost. Those four questions decide far more trades than any single reading of any single indicator.

None of this makes a market predictable. It makes uncertainty measurable, which is a smaller claim and a much more useful one.

Get in touch

Questions about the research or the methodology are welcome, as are disagreements about them.

• Emaildrnamlabs@gmail.com
• Websitedrnamlabs.com
• LinkedInnam-le-b41263ab
• GitHubnamlehai90
• X@namlehai
• YouTube@Drnamlabs