The bet: microstructure bounce.
Our inaugural walk-forward produced only nine out-of-sample trades total across five coins — far too few to separate signal from luck. The handful that fired were all stop-out losses, but on samples of one or two trades per coin that tells us nothing. This is underpowered, not killed — and not a quiet win we are hiding.
Two things starved it: the liquidation-cluster signal it leans on was tier-gated down to a degraded form, and projecting 4-hour funding/OI onto a 15-minute clock made its five-way entry condition line up almost never. The sparsity lesson here directly shaped how we designed the funding and momentum tests that followed.
underpowered — only 9 out-of-sample trades across 5 coins. There are too few out-of-sample trades to publish a per-coin table — showing one would imply a fair test we did not get. This is inconclusive on the data we have, not a result we are hiding.
Too few trades to test fairly — not a quiet win we are hiding.
Every trade we place — wins and losses, from real money — is on the live track record. This page is the research that decides what we will and won't run.
See the live track record →