Your backtest worked. Your trading didn't.
Edge isn't designed.
It's selected.
Most traders optimize the scorecard without ever testing the bet. You have a thesis. We'll tell you if it survives.
Our process
Define the question.
Evolutionary search finds what survives.
Every signal in your data can be transformed, lagged, and combined with every other, but you've only tested the combinations that made sense to you. The algorithm tests the rest.
Signals compete like traits in a population - the fittest survive, recombine, and mutate. The weak ones die off. No researcher picking winners. Just the data.
What survives isn't what you'd choose by hand. It's what the data couldn't kill.
Your thesis. The right question.
You've built intuition from watching markets for years, and we translate it into something measurable. But before we optimize anything, we figure out what's worth optimizing. Most traders go straight to tuning the dials - sizing, entries, exits - without asking whether they're turning the right ones. The same data answers completely different questions depending on what you're trying to predict. We start there.
Production
Your edge survived. Now it needs to run.
Data pipelines, historical-to-live matching, real-time execution. From data ingestion to deployed system - not a PDF.
If this sounds familiar - here's what the engagement looks like: a research engagement that starts with your thesis and ends with a verdict - and if it survives, a production system that trades it. See services
Why the results hold
No future information
Signals are stamped to what you'd actually know at decision time. Fills are modeled at realistic execution windows - not the close that generated the signal.
Execution realism
When your signal is strongest, the market is usually thinnest. We model that. Costs scale with conviction, not just volume.
Holdout validation
The search never touches out-of-sample data - not for signal selection, not for parameter tuning, not for stopping rules. One pass. No reruns.
In a recent engagement, we screened 47 candidate features. Four survived walk-forward validation with 88%+ stability. The resulting model's risk-adjusted return was three times buy-and-hold.
Most strategies don't survive the process.
The ones that do are worth trading.
Tell me what you're working on. I'll let you know if there's something testable.
Start a conversation