# Earnings Reversal (JP All Stocks)

- **Slug**: `earnings-reversal-short-jp-all`
- **Verdict**: rejected (no_edge)
- **Asset class**: equity
- **Categories**: earnings, event-driven, reversal
- **Source**: qbuntu-analysis (computed asof 2026-07-27T03:36:48)
- **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/earnings-reversal-short-jp-all
- **JSON**: https://qbuntu.ai/v1/strategies/earnings-reversal-short-jp-all
- **License**: CC-BY-4.0

## Hypothesis

Post-earnings price reactions tend to overshoot. Testing on the full Japanese stock universe.

## Why it didn't work

Across 2880 grid combinations, median Sharpe=-3.15, best=-0.76. Primary failure mode: no_edge.

## Performance summary

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

| Metric | Value |
|---|---|
| Sharpe (median) | -3.1493 |
| Max drawdown | -57% |
| p-value | 0.11 |
| Backtest period | 2023-12-18 to 2026-05-19 |

Sharpe distribution across 2880 grid runs: median -3.15, best -0.76 (best-case — not representative), worst -7.82, p25 -4.09, p75 -2.23.

## Methodology

- Notes: {"data_start": "2023-12-06 (earnings data availability)", "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-earnings-reversal-short-jp-all-0000` | side="SHORT_ONLY", cost_bps=5, n_positions=1, holding_period=1 | -4.02 | -3.44 | -5.4 | -1.97 |
| `r-earnings-reversal-short-jp-all-0001` | side="LONG_ONLY", cost_bps=5, n_positions=1, holding_period=1 | -3.09 | -4.49 | -3.86 | 8.35 |
| `r-earnings-reversal-short-jp-all-0002` | side="BOTH", cost_bps=5, n_positions=1, holding_period=1 | -3.84 | -4.09 | -5.8 | 0.37 |
| `r-earnings-reversal-short-jp-all-0009` | side="SHORT_ONLY", cost_bps=20, n_positions=1, holding_period=1 | -4.36 | -3.89 | -5.71 | -2.22 |
| `r-earnings-reversal-short-jp-all-0036` | side="SHORT_ONLY", cost_bps=5, n_positions=10, holding_period=1 | -4.03 | -2.9 | -5.71 | -0.16 |
| `r-earnings-reversal-short-jp-all-0134` | side="BOTH", cost_bps=5, n_positions=10, holding_period=1 | -3.52 | -2.64 | -5.7 | 2.06 |
| `r-earnings-reversal-short-jp-all-0264` | side="SHORT_ONLY", cost_bps=5, n_positions=5, holding_period=1 | -3.64 | -3.44 | -4.91 | 0.26 |
| `r-earnings-reversal-short-jp-all-0394` | side="LONG_ONLY", cost_bps=20, n_positions=1, holding_period=1 | -3.71 | -4.82 | -5.33 | 17.66 |
| `r-earnings-reversal-short-jp-all-0524` | side="BOTH", cost_bps=15, n_positions=10, holding_period=1 | -4.85 | -5.67 | -7.17 | 5.91 |
| `r-earnings-reversal-short-jp-all-0576` | side="SHORT_ONLY", cost_bps=5, n_positions=1, holding_period=1 | -5.07 | -4.89 | -8.28 | 8.32 |
| `r-earnings-reversal-short-jp-all-0655` | side="LONG_ONLY", cost_bps=15, n_positions=5, holding_period=1 | -6.28 | -6.51 | -5.07 | — |
| `r-earnings-reversal-short-jp-all-0785` | side="BOTH", cost_bps=10, n_positions=3, holding_period=2 | -4.05 | -3.46 | -5.56 | -0.16 |
| `r-earnings-reversal-short-jp-all-0915` | side="SHORT_ONLY", cost_bps=10, n_positions=1, holding_period=2 | -3.42 | -3.12 | -4.64 | -1.64 |
| `r-earnings-reversal-short-jp-all-1045` | side="LONG_ONLY", cost_bps=5, n_positions=10, holding_period=2 | -1.17 | -1.77 | -2.49 | 18.43 |
| `r-earnings-reversal-short-jp-all-1175` | side="BOTH", cost_bps=20, n_positions=3, holding_period=2 | -4.27 | -4.94 | -6.93 | 7.27 |
| `r-earnings-reversal-short-jp-all-1305` | side="SHORT_ONLY", cost_bps=20, n_positions=1, holding_period=2 | -7.82 | -7.48 | -11.29 | 8.47 |
| `r-earnings-reversal-short-jp-all-1306` | side="LONG_ONLY", cost_bps=20, n_positions=1, holding_period=2 | -3.49 | -0.72 | -10.43 | — |
| `r-earnings-reversal-short-jp-all-1436` | side="BOTH", cost_bps=15, n_positions=10, holding_period=2 | -5.75 | -3.42 | -10.96 | 8.5 |
| `r-earnings-reversal-short-jp-all-1566` | side="SHORT_ONLY", cost_bps=15, n_positions=5, holding_period=3 | -3.28 | -0.87 | -5.39 | 0.82 |
| `r-earnings-reversal-short-jp-all-1696` | side="LONG_ONLY", cost_bps=10, n_positions=3, holding_period=3 | -1.33 | -2.01 | -1.59 | 6.28 |
| `r-earnings-reversal-short-jp-all-1741` | side="LONG_ONLY", cost_bps=5, n_positions=3, holding_period=3 | -0.76 | -1.74 | -0.95 | 18.58 |
| `r-earnings-reversal-short-jp-all-1827` | side="SHORT_ONLY", cost_bps=10, n_positions=1, holding_period=3 | -3.1 | -1.32 | -6.59 | 1.18 |
| `r-earnings-reversal-short-jp-all-1957` | side="LONG_ONLY", cost_bps=5, n_positions=10, holding_period=3 | -2.15 | -3.65 | -2.08 | 18.58 |
| `r-earnings-reversal-short-jp-all-2087` | side="BOTH", cost_bps=20, n_positions=3, holding_period=3 | -4.21 | -3.34 | -6.29 | 8.47 |
| `r-earnings-reversal-short-jp-all-2160` | side="SHORT_ONLY", cost_bps=5, n_positions=1, holding_period=5 | -1.91 | 0.21 | -4.55 | 1.82 |
| `r-earnings-reversal-short-jp-all-2218` | side="LONG_ONLY", cost_bps=20, n_positions=1, holding_period=5 | -1.14 | -1.78 | -0.62 | 0.51 |
| `r-earnings-reversal-short-jp-all-2348` | side="BOTH", cost_bps=15, n_positions=10, holding_period=5 | -2.07 | -1.81 | -3.7 | 2.86 |
| `r-earnings-reversal-short-jp-all-2478` | side="SHORT_ONLY", cost_bps=15, n_positions=5, holding_period=5 | -2.71 | -0.38 | -5.82 | 3.71 |
| `r-earnings-reversal-short-jp-all-2608` | side="LONG_ONLY", cost_bps=10, n_positions=3, holding_period=5 | -1.81 | -3.12 | -1.19 | 18.5 |
| `r-earnings-reversal-short-jp-all-2738` | side="BOTH", cost_bps=5, n_positions=1, holding_period=5 | -3.73 | -2.35 | -6.25 | -0.68 |

## Facts (5)

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

- **Best grid Sharpe ratio is -0.76 (p=0.66).**
  - Value: -0.76 sharpe_ratio
  - Context: period 2023-12-18–2026-05-19; cost=5bps; side=LONG_ONLY
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/earnings-reversal-short-jp-all-fact-best-sharpe

- **Median Sharpe across 2880 grid runs is -3.15.**
  - Value: -3.15 sharpe_ratio
  - Context: Full grid of 2880 parameter combinations.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/earnings-reversal-short-jp-all-fact-median-sharpe

- **Median Sharpe in DOWN regime is 4.09 across 2880 runs.**
  - Value: 4.09 sharpe_ratio
  - Context: Regime=DOWN, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/earnings-reversal-short-jp-all-fact-regime-down

- **Median Sharpe in FLAT regime is -5.26 across 2880 runs.**
  - Value: -5.26 sharpe_ratio
  - Context: Regime=FLAT, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/earnings-reversal-short-jp-all-fact-regime-flat

- **Median Sharpe in UP regime is -2.86 across 2880 runs.**
  - Value: -2.86 sharpe_ratio
  - Context: Regime=UP, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/earnings-reversal-short-jp-all-fact-regime-up

## Related strategies

- same_strategy: [earnings-reversal-short-jp-growth](https://qbuntu.ai/strategies/earnings-reversal-short-jp-growth)
- same_data_source: [pead-jp-all](https://qbuntu.ai/strategies/pead-jp-all)

---

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

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