We teach machines to read the noise out of markets.
AI Automated Trading is a research and education company. We study how modern AI models interpret market data, publish what we learn, and build the tools that help traders and engineers understand signal processing, not shortcuts to profit.
Raw market data → resolved signal
14
Open-source research notes
6
Learning Center tracks
100%
Non-custodial by design
What we actually build
Four areas of applied research, documented in the open so anyone can evaluate the reasoning, not just the results.
Model research
We evaluate how transformer and time-series architectures behave on noisy, non-stationary market data — and publish what actually holds up.
Signal processing pipelines
Open documentation on the feature engineering and denoising techniques used before any model ever sees a data point.
Backtesting methodology
Guides on avoiding lookahead bias, overfitting, and survivorship bias — the failure modes that make results look better than they are.
Responsible framing
Every research note ships with its assumptions and limitations. We do not publish guarantees, because markets don't offer any.
Join the community, not a signal group.
Our Telegram channel is a place to learn and discuss — not a source of trade calls. We share the same research and questions publicly that we'd want to see before trusting an AI system with our own decisions.
Join on Telegram8,400+ members
Engineers, researchers, and traders discussing AI applied to markets.
Weekly office hours
Our research team answers questions live, every week.
Member-only notes
Early access to research write-ups before they're published publicly.
Frequently asked questions
Straight answers about what we are, what we're not, and how the research works.
Research notes, monthly.
One email a month: what we're learning about AI and market data, new Learning Center guides, and community updates. No noise, no hype.