# Mean Reversion (JP All Stocks)

- **Slug**: `mean-reversion-jp-all`
- **Verdict**: rejected (no_edge)
- **Asset class**: equity
- **Categories**: cross-sectional, factor, mean-reversion
- **Source**: qbuntu-analysis (computed asof 2026-07-27T03:37:08)
- **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/mean-reversion-jp-all
- **JSON**: https://qbuntu.ai/v1/strategies/mean-reversion-jp-all
- **License**: CC-BY-4.0

## Hypothesis

Stocks deviating from fair value revert to the mean. Testing 4 mean-reversion indicators on the full Japanese stock universe.

## Why it didn't work

Across 512 grid combinations, median Sharpe=-0.36, best=0.67. Primary failure mode: no_edge.

## Performance summary

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

| Metric | Value |
|---|---|
| Sharpe (median) | -0.3582 |
| Max drawdown | -22.3% |
| p-value | 0.43 |
| Backtest period | 2022-02-01 to 2026-02-02 |

Sharpe distribution across 512 grid runs: median -0.36, best 0.67 (best-case — not representative), worst -1.54, p25 -0.62, p75 -0.12.

## 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-mean-reversion-jp-all-0000` | cost_bps=5, lookback=10, n_stocks=5, indicator="zscore" | -0.78 | -0.72 | -0.75 | -1.52 |
| `r-mean-reversion-jp-all-0001` | cost_bps=5, lookback=10, n_stocks=5, indicator="zscore" | -0.78 | -0.69 | -0.75 | -1.52 |
| `r-mean-reversion-jp-all-0002` | cost_bps=10, lookback=10, n_stocks=5, indicator="zscore" | -1.03 | -0.91 | -1.02 | -1.86 |
| `r-mean-reversion-jp-all-0003` | cost_bps=10, lookback=10, n_stocks=5, indicator="zscore" | -1.04 | -0.88 | -1.02 | -1.86 |
| `r-mean-reversion-jp-all-0004` | cost_bps=5, lookback=10, n_stocks=10, indicator="zscore" | -0.88 | -1.54 | -0.56 | -2.35 |
| `r-mean-reversion-jp-all-0048` | cost_bps=5, lookback=10, n_stocks=5, indicator="zscore" | 0.14 | -0.18 | 0.24 | 0.22 |
| `r-mean-reversion-jp-all-0052` | cost_bps=5, lookback=10, n_stocks=10, indicator="zscore" | -0.21 | -1.34 | 0.25 | -1.04 |
| `r-mean-reversion-jp-all-0099` | cost_bps=10, lookback=20, n_stocks=5, indicator="zscore" | -0.78 | -1.66 | -0.59 | -1.67 |
| `r-mean-reversion-jp-all-0146` | cost_bps=10, lookback=40, n_stocks=5, indicator="zscore" | 0.1 | -0.57 | 0.42 | -0.76 |
| `r-mean-reversion-jp-all-0192` | cost_bps=5, lookback=60, n_stocks=5, indicator="zscore" | -0.18 | -0.49 | -0.25 | 1.29 |
| `r-mean-reversion-jp-all-0194` | cost_bps=10, lookback=60, n_stocks=5, indicator="zscore" | -0.4 | -0.83 | -0.45 | 1.07 |
| `r-mean-reversion-jp-all-0241` | cost_bps=5, lookback=60, n_stocks=5, indicator="zscore" | 0.5 | -0.34 | 0.87 | -3.22 |
| `r-mean-reversion-jp-all-0288` | cost_bps=5, lookback=10, n_stocks=5, indicator="rsi" | -0.3 | -1.11 | -0.14 | -0.94 |
| `r-mean-reversion-jp-all-0327` | cost_bps=10, lookback=20, n_stocks=10, indicator="rsi" | -0.82 | -0.55 | -0.9 | -0.37 |
| `r-mean-reversion-jp-all-0374` | cost_bps=10, lookback=20, n_stocks=10, indicator="rsi" | -0.55 | -3 | 0.12 | -0.22 |
| `r-mean-reversion-jp-all-0421` | cost_bps=5, lookback=40, n_stocks=10, indicator="rsi" | -0.07 | 0.34 | -0.1 | -0.76 |
| `r-mean-reversion-jp-all-0468` | cost_bps=5, lookback=60, n_stocks=10, indicator="rsi" | -0.28 | 0.41 | -0.58 | 0.57 |
| `r-mean-reversion-jp-all-0512` | cost_bps=5, lookback=10, n_stocks=5, indicator="bollinger_pct" | -0.78 | -0.72 | -0.75 | -1.52 |
| `r-mean-reversion-jp-all-0516` | cost_bps=5, lookback=10, n_stocks=10, indicator="bollinger_pct" | -0.88 | -1.54 | -0.56 | -2.35 |
| `r-mean-reversion-jp-all-0563` | cost_bps=10, lookback=10, n_stocks=5, indicator="bollinger_pct" | 0.17 | 0.23 | 0.15 | 0.17 |
| `r-mean-reversion-jp-all-0610` | cost_bps=10, lookback=20, n_stocks=5, indicator="bollinger_pct" | -0.78 | -1.41 | -0.59 | -1.67 |
| `r-mean-reversion-jp-all-0657` | cost_bps=5, lookback=40, n_stocks=5, indicator="bollinger_pct" | 0.25 | -0.85 | 0.57 | -0.67 |
| `r-mean-reversion-jp-all-0704` | cost_bps=5, lookback=60, n_stocks=5, indicator="bollinger_pct" | -0.18 | -0.49 | -0.25 | 1.29 |
| `r-mean-reversion-jp-all-0743` | cost_bps=10, lookback=60, n_stocks=10, indicator="bollinger_pct" | -0.4 | -0.23 | -0.31 | -1.53 |
| `r-mean-reversion-jp-all-0774` | cost_bps=10, lookback=10, n_stocks=10, indicator="mrs" | -1.54 | -1.78 | -1.66 | 0.92 |
| `r-mean-reversion-jp-all-0791` | cost_bps=10, lookback=10, n_stocks=10, indicator="mrs" | -0.15 | 1.12 | -0.77 | 1.31 |
| `r-mean-reversion-jp-all-0838` | cost_bps=10, lookback=20, n_stocks=10, indicator="mrs" | -1.44 | -1.49 | -1.33 | -2.38 |
| `r-mean-reversion-jp-all-0885` | cost_bps=5, lookback=20, n_stocks=10, indicator="mrs" | -0.18 | 0.31 | -0.12 | -7.27 |
| `r-mean-reversion-jp-all-0917` | cost_bps=5, lookback=40, n_stocks=10, indicator="mrs" | 0.67 | 1.93 | 0.54 | -11.55 |
| `r-mean-reversion-jp-all-0933` | cost_bps=5, lookback=40, n_stocks=10, indicator="mrs" | 0.54 | 1.66 | 0.62 | -5.37 |

## Facts (7)

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

- **Average monthly return correlation with other strategies in DOWN regime: 0.19**
  - Value: 0.1865 correlation
  - Context: Pairwise Pearson correlation of monthly returns across 42 strategies, filtered to DOWN regime months (N=3, N225 < SMA20 < SMA60)
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/mean-reversion-jp-all-fact-avg-corr-down

- **Average monthly return correlation with other strategies (full period): 0.04**
  - Value: 0.0425 correlation
  - Context: Pairwise Pearson correlation of monthly returns across 42 strategies, full backtest period
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/mean-reversion-jp-all-fact-avg-corr-full

- **Best grid Sharpe ratio is 0.67 (p=0.18).**
  - Value: 0.67 sharpe_ratio
  - Context: period 2022-02-01–2026-02-02; cost=5bps
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/mean-reversion-jp-all-fact-best-sharpe

- **Median Sharpe across 512 grid runs is -0.36.**
  - Value: -0.36 sharpe_ratio
  - Context: Full grid of 512 parameter combinations.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/mean-reversion-jp-all-fact-median-sharpe

- **Median Sharpe in DOWN regime is -1.27 across 512 runs.**
  - Value: -1.27 sharpe_ratio
  - Context: Regime=DOWN, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/mean-reversion-jp-all-fact-regime-down

- **Median Sharpe in FLAT regime is -0.31 across 512 runs.**
  - Value: -0.31 sharpe_ratio
  - Context: Regime=FLAT, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/mean-reversion-jp-all-fact-regime-flat

- **Median Sharpe in UP regime is -0.59 across 512 runs.**
  - Value: -0.59 sharpe_ratio
  - Context: Regime=UP, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/mean-reversion-jp-all-fact-regime-up

## Related strategies

- same_strategy: [mean-reversion-jp-growth](https://qbuntu.ai/strategies/mean-reversion-jp-growth)

---

Cite as: qbuntu (2026). Mean Reversion (JP All Stocks). https://qbuntu.ai/strategies/mean-reversion-jp-all

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