Olympia
Multi-Horizon Equities Intelligence

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 targetReturn outcomesDownside
Hourly — data as of 2026-10-21

Downside

what Hourly winners went through on the way to paying — the deepest drawdown, and what a stop would have cost — measured signal to the end of tracking (5 trading days). Not a hit rate.
Read this as risk, not recordHistorically, these winners dipped before they paid. The stop columns show what a stop of that size would have done to this population — winners it would have exited before the target, and how the average outcome moved. Historical data, not an instruction.

Basis: Hourly figures here are on the conservative-daily floor (the master's basis) — the extended-session downside is a separate pass.

ELITE67 winners · median worst moment -13.7%191 resolved123 still tracking10 not measurable
DrawdownShare of winners (anytime)…before the target
−5%+
82.1%(55)
62.7% (42)
−10%+
67.2%(45)
40.3% (27)
−15%+
46.3%(31)
20.9% (14)
−20%+
43.3%(29)
16.4% (11)
What a stop would have cost this lane
Exit ruleWinners it exitsAverage outcome
No stop — held to target—-9.5%
−5% price stop42 (62.7%)-2.4%
−10% price stop27 (40.3%)-4.6%
−15% price stop14 (20.9%)-5.7%
−25% price stop7 (10.4%)-8.0%
Time exit — day 310 (14.9%)-7.3%

“Winners it exits” counts winners whose deepest Low reached the stop before the target was touched (a price stop) or that touched after the exit day (the time exit). Average outcome is over all 191 resolved signals in this tier. Past behaviour, not a forecast.

HIGH341 winners · median worst moment -7.9%705 resolved75 still tracking15 not measurable
DrawdownShare of winners (anytime)…before the target
−5%+
64.8%(221)
41.3% (141)
−10%+
39.9%(136)
19.1% (65)
−15%+
24.1%(82)
8.5% (29)
−20%+
15.5%(53)
4.4% (15)
What a stop would have cost this lane
Exit ruleWinners it exitsAverage outcome
No stop — held to target—-1.7%
−5% price stop141 (41.3%)-0.5%
−10% price stop65 (19.1%)-1.1%
−15% price stop29 (8.5%)-1.5%
−25% price stop9 (2.6%)-1.8%
Time exit — day 346 (13.5%)-1.3%

“Winners it exits” counts winners whose deepest Low reached the stop before the target was touched (a price stop) or that touched after the exit day (the time exit). Average outcome is over all 705 resolved signals in this tier. Past behaviour, not a forecast.

MEDIUM1396 winners · median worst moment -3.8%7657 resolved1368 still tracking270 not measurable
DrawdownShare of winners (anytime)…before the target
−5%+
41.8%(583)
29.3% (409)
−10%+
17.9%(250)
9.6% (134)
−15%+
8.1%(113)
3.4% (47)
−20%+
3.0%(42)
0.9% (12)
What a stop would have cost this lane
Exit ruleWinners it exitsAverage outcome
No stop — held to target—-1.7%
−5% price stop409 (29.3%)-0.9%
−10% price stop134 (9.6%)-1.4%
−15% price stop47 (3.4%)-1.6%
−25% price stop1 (0.1%)-1.6%
Time exit — day 3465 (33.3%)-1.3%

“Winners it exits” counts winners whose deepest Low reached the stop before the target was touched (a price stop) or that touched after the exit day (the time exit). Average outcome is over all 7657 resolved signals in this tier. Past behaviour, not a forecast.

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.