From mechanism
to forecast.
We build causal models of the systems the world runs on: the atmosphere behind harvests, the climate behind risk, the grid behind power, the shocks that move prices and people. Built for everyone who has to act on what happens next.
Models of systems,
not curves.
Most forecasts fit the correlation and move on. We model the mechanism underneath it (identification, structure, the shape of the data-generating process) so the forecast survives when the regime changes.
Weather into softs, before it's price
An early-warning board for cocoa, coffee and sugar: where each crop's weather window sits now, against the anomalies that have historically moved price.
Which force is pricing EU carbon
A live regime monitor for EU allowances: whether industrial demand or MSR policy is setting the price right now, rebuilt every weekday from free public data.
The grid, from the inside
New England's gas-constrained winter grid: how electrification is bending load and price, and what a cold day now costs. Move the temperature, watch it reprice.
The one node that gates the chain
Rare-earth magnets are 3% of a robot's cost and 100% of its dependency, made overwhelmingly in one country. Push on the chokepoint and watch it cascade to EVs, wind and defense.
Built to order for the system you're exposed to. If it has a mechanism, we can model it.
Identify it. Validate it.
Deliver it.
Identify the mechanism
We start from the causal structure (what drives what, under which conditions), not from whatever correlation the last six months happen to show.
Validate on real data
Every model is tested on real, out-of-sample data. We publish the methodology and the results, including the ones that don't work.
Deliver the model
You receive a licensed, documented and monitored model: a signal, a forecast feed, or a full pricing layer that plugs into your stack.
If you depend on the
system, you can see it coming.
Our models are built for anyone whose decisions move with weather, climate, energy, food or the movement of people.
The same chains decide
more than prices.
Weather to harvest, shock to shortage, climate to displacement. These mechanisms decide harvests, outbreaks and migrations before they decide prices.
The commercial core of our work is in markets. The models are not. If you work in global health, food security, humanitarian response, disaster risk or migration, and an earlier, better forecast would change what you can do, write to us. We keep capacity for this work, and the absence of a budget is not a reason not to get in touch.
We show our work.
Public, empirical notes on real data. We publish method and results. The edge stays private; the rigour is on the table.