The record

Every signal each model has published, and what the price did afterwards — hit, missed, or still inside its window. Every number opens the trades behind it.

Time to target Return outcomes Downside

Daily — data as of 2026-10-21

Return outcomes

how far Daily signals ran, measured from the signal to the end of tracking (65 trading days)

ELITE186 reached +10% · median peak 32.9%201 resolved779 still tracking9 not measurable

Reached	Share of signals	Count	Median trading days to peak	25th–75th
+10%	92.5%	186	32	19–42
+20%	74.6%	150	32	19–44
+30%	55.7%	112	35	21–48
+50%	23.9%	48	40	28–56
+100%	7.5%	15	54	39–64
+150%	2.0%	4	54	52–57
+200%	1.5%	3	54	49–60

HIGH407 reached +10% · median peak 29.8%454 resolved699 still tracking3 not measurable

Reached	Share of signals	Count	Median trading days to peak	25th–75th
+10%	89.6%	407	34	21–52
+20%	69.4%	315	37	23–56
+30%	49.8%	226	46	29–61
+50%	28.2%	128	53	39–62
+100%	10.4%	47	55	44–62
+150%	3.1%	14	54	44–60
+200%	1.1%	5	62	58–65

MEDIUM407 reached +10% · median peak 31.7%462 resolved381 still tracking4 not measurable

Reached	Share of signals	Count	Median trading days to peak	25th–75th
+10%	88.1%	407	41	23–59
+20%	72.7%	336	44	31–61
+30%	53.5%	247	49	36–61
+50%	27.5%	127	50	41–62
+100%	7.4%	34	49	41–62
+150%	1.7%	8	52	35–61
+200%	0.4%	2	46	41–50

The top row is capped at +200%. Peak is measured on the adjusted daily high, so a stock split never reads as a move. Past performance does not predict future results. This is historical data, not investment advice. You are responsible for your own trading decisions.

Past performance does not predict future results. Historical blind walk-forward evidence, not investment advice.

The method behind these signals is published: OLYMPIA: Market-Regime-Conditioned Machine Learning for Equity Signal Generation — Rupert, Michael (Zenodo, 2026), DOI 10.5281/zenodo.18987223. The figures on this page are measured from the blind walk-forward record shown above, not taken from the paper.