The signal ledger, in numbers.
Aggregate statistics of every closed BUY-to-SELL signal on the Hesper Atlas public track record: win rates by year and by theme, the full return distribution, holding periods, and the best and worst signals ever produced. Regenerated after every US close from the same ledger, losers included.
As of 2026-08-20 03:31, the Hesper Atlas public ledger contains 570 closed BUY-to-SELL signals across 155 tracked names since 2022-05-25. 63.0% ended in profit; the average closed signal returned +38.8% over 134 days. The average winner made +66% while the average loser cost −7.4%, and 8.6% of all closed signals at least doubled.
Source: every figure on this page is computed from the machine-readable JSON ledger (field stats_ext), regenerated after every US close, losing signals included. Educational tool, not financial advice.
Results by year
Every closed signal, grouped by the year it exited. Trend engines earn their keep in trending years and get whipsawed in choppy ones; both show up here.
| Year | Signals | Ended in profit | Avg return |
|---|---|---|---|
| 2022 | 50 | 24.0% | −4.6% |
| 2023 | 130 | 60.8% | +10.2% |
| 2024 | 130 | 67.7% | +35% |
| 2025 | 157 | 72.6% | +52.6% |
| 2026 | 103 | 64.1% | +79.7% |
The current year contains only the signals that already closed; open positions join it when they exit.
What a closed signal looks like
The distribution behind the averages. A trend engine's math is asymmetry: it takes many small losses to stay in the game for the few very large wins.
Results by theme
Closed signals grouped by the theme of the underlying name, largest first.
| Theme | Signals | Ended in profit | Avg return |
|---|---|---|---|
| Genomics & AI-Health | 96 | 57.3% | +10.9% |
| AI Software | 63 | 60.3% | +32.9% |
| AI Power & Grid | 58 | 56.9% | +44.2% |
| AI Chips | 54 | 53.7% | +29.4% |
| Consumer & Internet | 51 | 70.6% | +14.3% |
| Fintech & Crypto | 38 | 60.5% | +43.5% |
| HBM & Packaging | 27 | 70.4% | +42.1% |
| Quantum | 24 | 54.2% | +84.4% |
| AI Servers & Systems | 18 | 72.2% | +78.8% |
| Energy | 16 | 68.8% | +5.5% |
| Industrials | 15 | 60.0% | +30.2% |
| AI Cloud | 15 | 66.7% | +103% |
Ten best closed signals
| Symbol | Entry | Exit | Return |
|---|---|---|---|
| AXTI | 2025-08-28 | 2026-06-10 | +2820.9% |
| PLTR | 2023-05-11 | 2026-01-28 | +1492.6% |
| IREN | 2025-05-01 | 2025-11-05 | +1099.5% |
| SMCI | 2022-08-12 | 2024-07-24 | +989.5% |
| RGTI | 2024-09-13 | 2025-02-26 | +987.9% |
| POWL | 2022-10-25 | 2025-02-18 | +809.8% |
| LITE | 2025-06-25 | 2026-07-06 | +696.8% |
| VRT | 2023-04-26 | 2025-01-27 | +656.3% |
| NVDA | 2022-12-09 | 2025-03-14 | +616.3% |
| RGTI | 2025-04-21 | 2025-10-17 | +471.9% |
Ten worst closed signals
| Symbol | Entry | Exit | Return |
|---|---|---|---|
| RGTI | 2024-07-15 | 2024-08-05 | −33.1% |
| MDB | 2022-08-11 | 2022-09-08 | −32.9% |
| TER | 2025-02-26 | 2025-04-25 | −32.8% |
| TEM | 2025-06-18 | 2026-03-20 | −32% |
| IREN | 2024-07-26 | 2024-08-07 | −29.1% |
| IONQ | 2023-09-11 | 2023-09-27 | −27.6% |
| NU | 2024-09-19 | 2025-02-28 | −27.4% |
| TER | 2022-08-12 | 2022-10-24 | −25.7% |
| AXTI | 2023-01-27 | 2023-02-24 | −22.9% |
| ON | 2024-02-22 | 2024-04-22 | −22.6% |
Held-out evaluation, separate from this ledger
The ledger above replays today's rules over history, so it inherits hindsight (the caveats below spell this out). The held-out evaluation is the harder test: each engine is tuned on the earlier part of a name's history and scored on the last 40% it never trained on, after costs, with next-day fills. As of the July 2026 evaluation across all 152 evaluated names: median worst drawdown -30% with the engine versus -57% buying and holding; 150 of 152 names had a shallower worst drop; median return +22.7% per year versus +18.9% holding. For scale over the same January 2022 to July 2026 stretch: cash returned about +4.1% a year, the S&P 500 about +11.9% and the Nasdaq 100 about +14.2% (total return with dividends). Backtested, not live. Method on the methodology page.
- These are the signals of TODAY'S engine replayed over history: the rules were researched and improved over time, so early-period signals are partly retrospective.
- The universe is today's catalog (survivorship-biased: it contains names that earned their place; delisted or faded names aren't represented).
- Returns are raw per-signal price returns (dividend-adjusted), end-of-day, without position sizing, costs or slippage; the in-app backtests apply 0.1% round-trip costs and vol-targeted sizing.
- A trend engine exits AFTER tops and enters AFTER bottoms by design; win rate matters less than the size of wins vs losses.
- Past performance (measured or backtested) does not predict future results. Educational tool, not investment advice.
stats_ext) · Educational tool, not investment advice ·
Past performance (measured or backtested) does not predict future results.
Open Hesper Atlas →