# Gap Reversal (JP All Stocks)

- **Slug**: `gap-reversal-short-jp-all`
- **Verdict**: rejected (no_edge)
- **Asset class**: equity
- **Categories**: gap, intraday, mean-reversion
- **Source**: qbuntu-analysis (computed asof 2026-07-27T03:36:26)
- **Reproducibility**: analysis-engine@bfafe7d, backtest-lib@711b855, grid tier=shallow (python 3.10.11, numpy 2.2.6, pandas 2.3.3)
- **HTML**: https://qbuntu.ai/strategies/gap-reversal-short-jp-all
- **JSON**: https://qbuntu.ai/v1/strategies/gap-reversal-short-jp-all
- **License**: CC-BY-4.0

## Hypothesis

Overnight gaps across all Japanese stocks tend to reverse. Testing the same gap-reversal signal on the full universe.

## Why it didn't work

Across 1728 grid combinations, median Sharpe=-0.75, best=0.69. Primary failure mode: no_edge.

## Performance summary

Headline figures are the **median across the parameter grid**, not the best run.

| Metric | Value |
|---|---|
| Sharpe (median) | -0.7486 |
| Max drawdown | -4.5% |
| p-value | 0.12 |
| Backtest period | 2022-01-07 to 2026-05-19 |

Sharpe distribution across 1728 grid runs: median -0.75, best 0.69 (best-case — not representative), worst -1.66, p25 -1.08, p75 -0.17.

## Methodology

- Notes: {"walk_forward_definition": {"type": "single_pass", "description": "Full period backtest without walk-forward split", "verdict_basis": "full_period"}}
- Slippage model: open-on-open + variable bps fixed
- Position sizing: equal_weight
- Regime definition: N225 SMA20/SMA60 three-class
- Transaction cost bps: 5

## Target universe

Tokyo Stock Exchange all listed (Prime/Standard/Growth), ~3747 stocks

## Runs (30)

| run_id | params | sharpe | UP | FLAT | DOWN |
|---|---|---:|---:|---:|---:|
| `r-gap-reversal-short-jp-all-0000` | side="SHORT", top_n=10, cost_bps=3, hold_days=1 | -0.9 | -1.76 | -1.84 | -4.97 |
| `r-gap-reversal-short-jp-all-0001` | side="SHORT", top_n=10, cost_bps=5, hold_days=1 | -0.94 | -1.89 | -1.96 | -5.07 |
| `r-gap-reversal-short-jp-all-0002` | side="SHORT", top_n=10, cost_bps=10, hold_days=1 | -1.05 | -2.21 | -2.28 | -5.33 |
| `r-gap-reversal-short-jp-all-0006` | side="BOTH", top_n=10, cost_bps=3, hold_days=1 | -1.15 | -3.97 | -2.74 | 0.58 |
| `r-gap-reversal-short-jp-all-0009` | side="SHORT", top_n=10, cost_bps=3, hold_days=1 | -0.84 | — | -1.84 | -4.97 |
| `r-gap-reversal-short-jp-all-0018` | side="SHORT", top_n=10, cost_bps=3, hold_days=1 | -0.66 | 5.08 | -1.77 | -4.97 |
| `r-gap-reversal-short-jp-all-0081` | side="SHORT", top_n=10, cost_bps=3, hold_days=5 | -1.62 | -4.18 | -3.78 | -9.45 |
| `r-gap-reversal-short-jp-all-0083` | side="SHORT", top_n=10, cost_bps=10, hold_days=5 | -1.66 | -4.28 | -3.92 | -9.63 |
| `r-gap-reversal-short-jp-all-0092` | side="SHORT", top_n=10, cost_bps=10, hold_days=5 | -1.49 | — | -3.92 | -9.63 |
| `r-gap-reversal-short-jp-all-0177` | side="BOTH", top_n=10, cost_bps=3, hold_days=3 | -0.98 | -6.44 | -3.18 | -2.55 |
| `r-gap-reversal-short-jp-all-0262` | side="SHORT", top_n=10, cost_bps=5, hold_days=2 | -1.12 | -53.28 | -5.94 | -11.8 |
| `r-gap-reversal-short-jp-all-0300` | side="LONG", top_n=10, cost_bps=3, hold_days=5 | 0.69 | -12.03 | 5.2 | 15.61 |
| `r-gap-reversal-short-jp-all-0324` | side="SHORT", top_n=10, cost_bps=3, hold_days=1 | -0.11 | 8.89 | 3.91 | -5.73 |
| `r-gap-reversal-short-jp-all-0349` | side="BOTH", top_n=10, cost_bps=5, hold_days=1 | -0.43 | -6.48 | 5.41 | -4.79 |
| `r-gap-reversal-short-jp-all-0434` | side="SHORT", top_n=20, cost_bps=10, hold_days=1 | -1.05 | -2.21 | -2.28 | -5.33 |
| `r-gap-reversal-short-jp-all-0519` | side="BOTH", top_n=20, cost_bps=3, hold_days=5 | -0.88 | -5.13 | -1.98 | 1.75 |
| `r-gap-reversal-short-jp-all-0604` | side="SHORT", top_n=20, cost_bps=5, hold_days=3 | -1.09 | — | -4.72 | -8.3 |
| `r-gap-reversal-short-jp-all-0689` | side="LONG", top_n=20, cost_bps=10, hold_days=2 | 0.17 | -12.2 | -0.44 | 9.64 |
| `r-gap-reversal-short-jp-all-0774` | side="SHORT", top_n=20, cost_bps=3, hold_days=1 | -0.11 | — | 3.91 | -5.73 |
| `r-gap-reversal-short-jp-all-0859` | side="LONG", top_n=20, cost_bps=5, hold_days=5 | 0.59 | -12.11 | 4.53 | 12.56 |
| `r-gap-reversal-short-jp-all-0944` | side="BOTH", top_n=50, cost_bps=10, hold_days=3 | -1.3 | -6.97 | -2 | -2.69 |
| `r-gap-reversal-short-jp-all-1029` | side="LONG", top_n=50, cost_bps=3, hold_days=3 | -0.08 | -6.44 | 0.91 | 7.72 |
| `r-gap-reversal-short-jp-all-1114` | side="BOTH", top_n=50, cost_bps=5, hold_days=2 | -0.71 | -7.64 | -4.43 | 1.54 |
| `r-gap-reversal-short-jp-all-1199` | side="SHORT", top_n=50, cost_bps=10, hold_days=1 | -0.3 | — | 3.44 | -5.96 |
| `r-gap-reversal-short-jp-all-1284` | side="BOTH", top_n=50, cost_bps=3, hold_days=5 | 0.07 | -12.03 | -2.18 | 4.47 |
| `r-gap-reversal-short-jp-all-1296` | side="SHORT", top_n=100, cost_bps=3, hold_days=1 | -0.9 | -1.76 | -1.84 | -4.97 |
| `r-gap-reversal-short-jp-all-1370` | side="SHORT", top_n=100, cost_bps=10, hold_days=3 | -1.3 | -8.79 | -2.88 | -8.17 |
| `r-gap-reversal-short-jp-all-1455` | side="BOTH", top_n=100, cost_bps=3, hold_days=2 | -0.96 | -9.69 | -3.59 | 1.97 |
| `r-gap-reversal-short-jp-all-1540` | side="SHORT", top_n=100, cost_bps=5, hold_days=2 | -1.12 | -6.14 | -5.94 | -11.8 |
| `r-gap-reversal-short-jp-all-1625` | side="LONG", top_n=100, cost_bps=10, hold_days=1 | -0.68 | -14.55 | 10.49 | -3.27 |

## Facts (5)

Each fact has a permanent citation URL. AI agents quoting qbuntu should use these.

- **Best grid Sharpe ratio is 0.69 (p=0.15).**
  - Value: 0.69 sharpe_ratio
  - Context: period 2022-01-07–2026-05-19; cost=3bps; side=LONG
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/gap-reversal-short-jp-all-fact-best-sharpe

- **Median Sharpe across 1728 grid runs is -0.75.**
  - Value: -0.75 sharpe_ratio
  - Context: Full grid of 1728 parameter combinations.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/gap-reversal-short-jp-all-fact-median-sharpe

- **Median Sharpe in DOWN regime is -2.18 across 1728 runs.**
  - Value: -2.18 sharpe_ratio
  - Context: Regime=DOWN, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/gap-reversal-short-jp-all-fact-regime-down

- **Median Sharpe in FLAT regime is -2.85 across 1728 runs.**
  - Value: -2.85 sharpe_ratio
  - Context: Regime=FLAT, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/gap-reversal-short-jp-all-fact-regime-flat

- **Median Sharpe in UP regime is -8.62 across 1728 runs.**
  - Value: -8.62 sharpe_ratio
  - Context: Regime=UP, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/gap-reversal-short-jp-all-fact-regime-up

## Related strategies

- same_strategy: [gap-reversal-short-jp-growth](https://qbuntu.ai/strategies/gap-reversal-short-jp-growth)

---

Cite as: qbuntu (2026). Gap Reversal (JP All Stocks). https://qbuntu.ai/strategies/gap-reversal-short-jp-all

Visit qbuntu.ai — the honest scorecard for quant strategies (live, promising, marginal, rejected).