# Multi-Factor Composite (JP All Stocks)

- **Slug**: `multi-factor-jp-all`
- **Verdict**: rejected (regime_dependent)
- **Asset class**: equity
- **Categories**: composite, cross-sectional, multi-factor
- **Source**: qbuntu-analysis (computed asof 2026-07-29T01:08:35)
- **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/multi-factor-jp-all
- **JSON**: https://qbuntu.ai/v1/strategies/multi-factor-jp-all
- **License**: CC-BY-4.0

## Hypothesis

Combines signals from marginal/promising single factors into a z-scored composite. Testing on the full Japanese stock universe.

## Why it didn't work

Across 120 grid combinations, median Sharpe=-0.25, best=0.41. Primary failure mode: regime_dependent.

## Performance summary

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

| Metric | Value |
|---|---|
| Sharpe (median) | -0.2509 |
| Max drawdown | -28% |
| p-value | 0.52 |
| Backtest period | 2022-02-01 to 2026-02-02 |

Sharpe distribution across 120 grid runs: median -0.25, best 0.41 (best-case — not representative), worst -1.29, p25 -0.56, p75 -0.03.

## 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-multi-factor-jp-all-0000` | cost_bps=5, n_stocks=5, n_factors=2, regime_gate=false | -0.85 | -1.71 | -0.49 | -4.14 |
| `r-multi-factor-jp-all-0001` | cost_bps=5, n_stocks=5, n_factors=2, regime_gate=true | -0.78 | -1.76 | -0.49 | -4.14 |
| `r-multi-factor-jp-all-0002` | cost_bps=10, n_stocks=5, n_factors=2, regime_gate=false | -1.07 | -1.91 | -0.7 | -4.57 |
| `r-multi-factor-jp-all-0003` | cost_bps=10, n_stocks=5, n_factors=2, regime_gate=true | -0.99 | -1.92 | -0.7 | -4.57 |
| `r-multi-factor-jp-all-0004` | cost_bps=5, n_stocks=10, n_factors=2, regime_gate=false | -0.87 | -2.47 | -0.13 | -6.65 |
| `r-multi-factor-jp-all-0017` | cost_bps=5, n_stocks=5, n_factors=2, regime_gate=true | -0.02 | 0.26 | 0.17 | -6.81 |
| `r-multi-factor-jp-all-0022` | cost_bps=10, n_stocks=10, n_factors=2, regime_gate=false | -0.86 | -2.05 | -0.2 | -6.67 |
| `r-multi-factor-jp-all-0035` | cost_bps=10, n_stocks=5, n_factors=2, regime_gate=true | -0.21 | 0.44 | 0 | -5.38 |
| `r-multi-factor-jp-all-0048` | cost_bps=5, n_stocks=5, n_factors=2, regime_gate=false | -0.24 | -2.13 | 0.39 | -4.71 |
| `r-multi-factor-jp-all-0053` | cost_bps=5, n_stocks=10, n_factors=2, regime_gate=true | -0.14 | -0.19 | 0.09 | -3.65 |
| `r-multi-factor-jp-all-0064` | cost_bps=5, n_stocks=5, n_factors=2, regime_gate=false | -0.19 | -0.7 | 0.08 | -1.85 |
| `r-multi-factor-jp-all-0067` | cost_bps=10, n_stocks=5, n_factors=2, regime_gate=true | -0.03 | 0.05 | 0.06 | -1.89 |
| `r-multi-factor-jp-all-0080` | cost_bps=5, n_stocks=5, n_factors=3, regime_gate=false | -0.53 | -1.85 | -0.11 | 0.52 |
| `r-multi-factor-jp-all-0085` | cost_bps=5, n_stocks=10, n_factors=3, regime_gate=true | -0.42 | -1.48 | -0.08 | -3.04 |
| `r-multi-factor-jp-all-0098` | cost_bps=10, n_stocks=5, n_factors=3, regime_gate=false | -0.5 | -1.58 | 0.08 | -0.88 |
| `r-multi-factor-jp-all-0103` | cost_bps=10, n_stocks=10, n_factors=3, regime_gate=true | 0.05 | 0.37 | 0.17 | -6.8 |
| `r-multi-factor-jp-all-0116` | cost_bps=5, n_stocks=10, n_factors=3, regime_gate=false | -0.15 | -0.88 | 0.37 | -4.42 |
| `r-multi-factor-jp-all-0129` | cost_bps=5, n_stocks=5, n_factors=3, regime_gate=true | 0.41 | 0.76 | 0.57 | -5.59 |
| `r-multi-factor-jp-all-0130` | cost_bps=10, n_stocks=5, n_factors=3, regime_gate=false | 0.02 | -0.79 | 0.51 | -5.72 |
| `r-multi-factor-jp-all-0135` | cost_bps=10, n_stocks=10, n_factors=3, regime_gate=true | 0.01 | 0.25 | 0.17 | -2.59 |
| `r-multi-factor-jp-all-0148` | cost_bps=5, n_stocks=10, n_factors=3, regime_gate=false | -0.16 | -0.06 | -0.02 | -5.83 |
| `r-multi-factor-jp-all-0160` | cost_bps=5, n_stocks=5, n_factors=4, regime_gate=false | -0.72 | -2.44 | -0.14 | -0.52 |
| `r-multi-factor-jp-all-0162` | cost_bps=10, n_stocks=5, n_factors=4, regime_gate=false | -0.94 | -2.62 | -0.39 | -0.74 |
| `r-multi-factor-jp-all-0166` | cost_bps=10, n_stocks=10, n_factors=4, regime_gate=false | -1.29 | -2.87 | -0.8 | -3.08 |
| `r-multi-factor-jp-all-0176` | cost_bps=5, n_stocks=5, n_factors=4, regime_gate=false | -0.5 | -1.86 | 0.24 | -1.28 |
| `r-multi-factor-jp-all-0181` | cost_bps=5, n_stocks=10, n_factors=4, regime_gate=true | -0.13 | 0.48 | -0.08 | -5.26 |
| `r-multi-factor-jp-all-0194` | cost_bps=10, n_stocks=5, n_factors=4, regime_gate=false | -0.78 | -1.79 | -0.23 | -4.59 |
| `r-multi-factor-jp-all-0199` | cost_bps=10, n_stocks=10, n_factors=4, regime_gate=true | -0.26 | 0.47 | -0.21 | -2.93 |
| `r-multi-factor-jp-all-0212` | cost_bps=5, n_stocks=10, n_factors=4, regime_gate=false | -0.12 | -1.43 | 0.41 | -2.16 |
| `r-multi-factor-jp-all-0225` | cost_bps=5, n_stocks=5, n_factors=4, regime_gate=true | -0.24 | -0.54 | -0.06 | -1.13 |

## Facts (5)

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

- **Best grid Sharpe ratio is 0.41 (p=0.41).**
  - Value: 0.41 sharpe_ratio
  - Context: period 2022-02-01–2026-02-02; cost=5bps
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/multi-factor-jp-all-fact-best-sharpe

- **Median Sharpe across 120 grid runs is -0.25.**
  - Value: -0.25 sharpe_ratio
  - Context: Full grid of 120 parameter combinations.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/multi-factor-jp-all-fact-median-sharpe

- **Median Sharpe in DOWN regime is -3.71 across 120 runs.**
  - Value: -3.71 sharpe_ratio
  - Context: Regime=DOWN, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/multi-factor-jp-all-fact-regime-down

- **Median Sharpe in FLAT regime is 0.07 across 120 runs.**
  - Value: 0.07 sharpe_ratio
  - Context: Regime=FLAT, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/multi-factor-jp-all-fact-regime-flat

- **Median Sharpe in UP regime is -0.85 across 120 runs.**
  - Value: -0.85 sharpe_ratio
  - Context: Regime=UP, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/multi-factor-jp-all-fact-regime-up

## Related strategies

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

---

Cite as: qbuntu (2026). Multi-Factor Composite (JP All Stocks). https://qbuntu.ai/strategies/multi-factor-jp-all

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