413
Markets tracked
Commodities, mining, shipping, semiconductors. Our agents measure when each market behaves differently — and discard everything that fails to beat chance.
The same measurement runs on a refinery and on a memory maker. What changes is the hour at which each one moves.
Every asset is put through the same examination, in both directions, with the cost of trading it carried from the first line.
Markets keep hours. We look for the ones where an asset behaves differently, and score what we find on return, consistency and significance.
A concentrated book drawn from a screened universe. Positions change when the evidence changes, not when the ranking wobbles.
The book runs against real prices and keeps its own history, day by day, so results are read from what happened rather than from what was fitted.
Several engines run the same research to different ends — return, consistency, or the balance between them — and are held to their own record.
Test enough hypotheses and some will look extraordinary by luck alone. Every result is measured against what chance would have produced from the same number of attempts.
A pattern is scored on ground it has not seen. One that only works where it was found is never called robust.
We subtract what plain exposure would have returned over the same hours. A rising asset makes any long strategy look good — that is not a signal.
Gross results are never presented as attainable. Execution cost enters the score itself, not a footnote beneath it.
Sweeps, portfolios, live execution and a daily record of results.