Predictions · every call that earned it · 30-day
Every crypto call in the next 30 days that earned it out of sample
0 calls over the next 30 days earned it out of sample as of Nov 4, 2026, on 0 coins: 0 higher, 0 lower, best record first.
Prediction from past patterns, not financial advice.
No call cleared the bar in the next 30 days. No coin has a 30-day call that held up out of sample (right more often than that side won on any day, on 100+ scored calls over 60+ separate days, with an average move its way above 0%), so none is listed.
every coin's 30-day prediction → · these calls as JSON (free API) →
Where the calls come from
A call is listed only when its kind of call earned it: counting every day once, its side was right more often than that same side won on any day of the coin's quarter, in both halves of the quarters walked, at a Newey-West t of 1.645 or more, on 100 or more scored calls over 60 or more separate days, and the average move on the call's side was above 0%, overall and in both halves. Each comes from one of four places: a proven driver in play on the coin (an event that moved it before), a likely driver (weaker evidence, walked apart), our own prediction's band, or all our data combined - one model that weighs everything we collect, with a chance for every coin, its calls kept apart by how sure they are.
A price call says higher or lower. A call against the altcoin average says stronger or weaker than the average of the 100 most traded altcoins: it is not a price direction. When a coin's price calls point both ways, both are listed (its calls disagree) and the coin is no best play.