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

Weekly — data as of 2026-10-16

Return outcomes

how far Weekly signals ran, measured from the signal to the end of tracking (130 trading days)

ELITE3193 reached +10% · median peak 48.1%3683 resolved3408 still tracking

Reached	Share of signals	Count	Median trading days to peak	25th–75th
+10%	86.7%	3193	74	30–110
+20%	76.2%	2807	80	39–112
+30%	66.2%	2438	85	48–114
+50%	48.3%	1780	92	60–118
+100%	25.1%	926	101	70–122
+150%	13.7%	505	106	76–123
+200%	8.8%	323	109	78–125

HIGH3358 reached +10% · median peak 43.9%3947 resolved3845 still tracking

Reached	Share of signals	Count	Median trading days to peak	25th–75th
+10%	85.1%	3358	66	24–109
+20%	73.2%	2888	75	34–112
+30%	62.1%	2451	83	43–115
+50%	45.6%	1799	90	54–118
+100%	22.7%	897	98	63–121
+150%	12.3%	485	101	65–123
+200%	7.3%	290	103	66–125

MEDIUM6785 reached +10% · median peak 41.0%7951 resolved6500 still tracking

Reached	Share of signals	Count	Median trading days to peak	25th–75th
+10%	85.3%	6785	68	30–108
+20%	72.1%	5729	76	39–112
+30%	60.4%	4803	82	46–115
+50%	42.6%	3390	90	56–118
+100%	19.1%	1516	98	63–122
+150%	9.7%	771	99	61–122
+200%	5.5%	435	98	55–122

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.