# Cross-Sectional Dispersion Trading (JP All Stocks)

- **Slug**: `dispersion-jp-all`
- **Verdict**: rejected (no_edge)
- **Asset class**: equity
- **Categories**: dispersion, regime, timing
- **Source**: qbuntu-analysis (computed asof 2026-07-31T01:32:26)
- **Reproducibility**: analysis-engine@18193e9, backtest-lib@711b855, grid tier=shallow (python 3.10.11, numpy 2.2.6, pandas 2.3.3)
- **HTML**: https://qbuntu.ai/strategies/dispersion-jp-all
- **JSON**: https://qbuntu.ai/v1/strategies/dispersion-jp-all
- **License**: CC-BY-4.0

## Hypothesis

Stivers (2010), Jiang (2010): cross-sectional return dispersion as a market timing signal. Testing on the full Japanese stock universe.

## Why it didn't work

Across 192 grid combinations, median Sharpe=-0.16, best=0.57. Primary failure mode: no_edge.

## Performance summary

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

| Metric | Value |
|---|---|
| Sharpe (median) | -0.1595 |
| Max drawdown | -31.3% |
| p-value | 0.49 |
| Backtest period | 2022-03-01 to 2026-02-02 |

Sharpe distribution across 192 grid runs: median -0.16, best 0.57 (best-case — not representative), worst -0.95, p25 -0.37, p75 0.05.

## 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-dispersion-jp-all-0000` | cost_bps=5, n_stocks=5, base_signal="momentum_20", holding_days=5 | -0.5 | 0.3 | -0.54 | -1.84 |
| `r-dispersion-jp-all-0001` | cost_bps=10, n_stocks=5, base_signal="momentum_20", holding_days=5 | -0.64 | 0.11 | -0.67 | -1.96 |
| `r-dispersion-jp-all-0002` | cost_bps=5, n_stocks=10, base_signal="momentum_20", holding_days=5 | 0.57 | 1.58 | 0.23 | 0.18 |
| `r-dispersion-jp-all-0003` | cost_bps=10, n_stocks=10, base_signal="momentum_20", holding_days=5 | 0.41 | 1.45 | 0.05 | 0.05 |
| `r-dispersion-jp-all-0008` | cost_bps=5, n_stocks=5, base_signal="momentum_60", holding_days=5 | 0.03 | 0.38 | 0.03 | -1.18 |
| `r-dispersion-jp-all-0016` | cost_bps=5, n_stocks=5, base_signal="mean_reversion", holding_days=5 | -0.34 | -0.66 | -0.29 | -0.08 |
| `r-dispersion-jp-all-0019` | cost_bps=10, n_stocks=10, base_signal="mean_reversion", holding_days=5 | -0.95 | -2.23 | -0.43 | -1.12 |
| `r-dispersion-jp-all-0026` | cost_bps=5, n_stocks=10, base_signal="momentum_20", holding_days=10 | 0.44 | 1.75 | 0.08 | 0.21 |
| `r-dispersion-jp-all-0042` | cost_bps=5, n_stocks=10, base_signal="mean_reversion", holding_days=10 | -0.78 | -2.55 | -0.41 | -0.2 |
| `r-dispersion-jp-all-0058` | cost_bps=5, n_stocks=10, base_signal="momentum_60", holding_days=20 | -0.07 | 1.36 | -0.69 | 2.29 |
| `r-dispersion-jp-all-0072` | cost_bps=5, n_stocks=5, base_signal="momentum_20", holding_days=60 | -0.2 | 0.75 | -0.54 | 2.48 |
| `r-dispersion-jp-all-0075` | cost_bps=10, n_stocks=10, base_signal="momentum_20", holding_days=60 | 0.17 | 1.67 | -0.25 | 3.6 |
| `r-dispersion-jp-all-0091` | cost_bps=10, n_stocks=10, base_signal="mean_reversion", holding_days=60 | -0.29 | -0.92 | -0.03 | -10.01 |
| `r-dispersion-jp-all-0107` | cost_bps=10, n_stocks=10, base_signal="momentum_60", holding_days=5 | 0.14 | 0.48 | 0.01 | -0.43 |
| `r-dispersion-jp-all-0123` | cost_bps=10, n_stocks=10, base_signal="momentum_20", holding_days=10 | 0.34 | 1.65 | -0.03 | 0.14 |
| `r-dispersion-jp-all-0139` | cost_bps=10, n_stocks=10, base_signal="mean_reversion", holding_days=10 | -0.89 | -2.67 | -0.53 | -0.27 |
| `r-dispersion-jp-all-0155` | cost_bps=10, n_stocks=10, base_signal="momentum_60", holding_days=20 | -0.16 | 1.28 | -0.79 | 2.07 |
| `r-dispersion-jp-all-0171` | cost_bps=10, n_stocks=10, base_signal="momentum_20", holding_days=60 | 0.17 | 1.67 | -0.25 | 3.6 |
| `r-dispersion-jp-all-0187` | cost_bps=10, n_stocks=10, base_signal="mean_reversion", holding_days=60 | -0.29 | -0.92 | -0.03 | -10.01 |
| `r-dispersion-jp-all-0203` | cost_bps=10, n_stocks=10, base_signal="momentum_60", holding_days=5 | 0.14 | 0.48 | 0.01 | -0.43 |
| `r-dispersion-jp-all-0219` | cost_bps=10, n_stocks=10, base_signal="momentum_20", holding_days=10 | 0.34 | 1.65 | -0.03 | 0.14 |
| `r-dispersion-jp-all-0235` | cost_bps=10, n_stocks=10, base_signal="mean_reversion", holding_days=10 | -0.85 | -2.67 | -0.47 | -0.27 |
| `r-dispersion-jp-all-0251` | cost_bps=10, n_stocks=10, base_signal="momentum_60", holding_days=20 | -0.16 | 1.28 | -0.79 | 2.07 |
| `r-dispersion-jp-all-0267` | cost_bps=10, n_stocks=10, base_signal="momentum_20", holding_days=60 | 0.17 | 1.67 | -0.25 | 3.6 |
| `r-dispersion-jp-all-0283` | cost_bps=10, n_stocks=10, base_signal="mean_reversion", holding_days=60 | -0.26 | -0.92 | 0.02 | -10.01 |
| `r-dispersion-jp-all-0288` | cost_bps=5, n_stocks=5, base_signal="momentum_20", holding_days=5 | -0.5 | 0.3 | -0.54 | -1.84 |
| `r-dispersion-jp-all-0304` | cost_bps=5, n_stocks=5, base_signal="mean_reversion", holding_days=5 | -0.32 | -0.66 | -0.25 | -0.08 |
| `r-dispersion-jp-all-0320` | cost_bps=5, n_stocks=5, base_signal="momentum_60", holding_days=10 | 0.14 | 0.67 | -0.2 | 2.14 |
| `r-dispersion-jp-all-0336` | cost_bps=5, n_stocks=5, base_signal="momentum_20", holding_days=20 | -0.37 | 1.18 | -0.9 | -0.15 |
| `r-dispersion-jp-all-0352` | cost_bps=5, n_stocks=5, base_signal="mean_reversion", holding_days=20 | 0.05 | -2.06 | 0.71 | -1.66 |

## Facts (5)

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

- **Best grid Sharpe ratio is 0.57 (p=0.25).**
  - Value: 0.57 sharpe_ratio
  - Context: period 2022-03-01–2026-02-02; cost=5bps
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/dispersion-jp-all-fact-best-sharpe

- **Median Sharpe across 192 grid runs is -0.16.**
  - Value: -0.16 sharpe_ratio
  - Context: Full grid of 192 parameter combinations.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/dispersion-jp-all-fact-median-sharpe

- **Median Sharpe in DOWN regime is -0.18 across 192 runs.**
  - Value: -0.18 sharpe_ratio
  - Context: Regime=DOWN, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/dispersion-jp-all-fact-regime-down

- **Median Sharpe in FLAT regime is -0.25 across 192 runs.**
  - Value: -0.25 sharpe_ratio
  - Context: Regime=FLAT, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/dispersion-jp-all-fact-regime-flat

- **Median Sharpe in UP regime is 0.43 across 192 runs.**
  - Value: 0.43 sharpe_ratio
  - Context: Regime=UP, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/dispersion-jp-all-fact-regime-up

## Related strategies

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

---

Cite as: qbuntu (2026). Cross-Sectional Dispersion Trading (JP All Stocks). https://qbuntu.ai/strategies/dispersion-jp-all

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