# Risk Parity / Volatility Targeting Overlay (JP Growth Stocks)

- **Slug**: `risk-parity-jp-growth`
- **Verdict**: rejected (no_edge)
- **Asset class**: equity
- **Categories**: overlay, risk-parity, volatility-targeting
- **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/risk-parity-jp-growth
- **JSON**: https://qbuntu.ai/v1/strategies/risk-parity-jp-growth
- **License**: CC-BY-4.0

## Hypothesis

Sizing positions inversely proportional to their recent volatility improves Sharpe ratio (risk parity principle). Tests vol-targeting as a position sizing overlay on momentum and mean-reversion base signals.

## Why it didn't work

Across 384 grid combinations, median Sharpe=-0.45, best=0.47. Primary failure mode: no_edge.

## Performance summary

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

| Metric | Value |
|---|---|
| Sharpe (median) | -0.4537 |
| Max drawdown | -38.8% |
| p-value | 0.34 |
| Backtest period | 2022-05-02 to 2026-06-01 |

Sharpe distribution across 384 grid runs: median -0.45, best 0.47 (best-case — not representative), worst -1.01, p25 -0.67, p75 -0.13.

## 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: volatility_targeted
- Regime definition: N225 SMA20/SMA60 three-class
- Transaction cost bps: 5

## Target universe

Tokyo Stock Exchange Growth Market, ~495 stocks, tv >= 30M JPY

## Runs (30)

| run_id | params | sharpe | UP | FLAT | DOWN |
|---|---|---:|---:|---:|---:|
| `r-risk-parity-jp-growth-0000` | cost_bps=5, target_vol=0.1, base_signal="momentum_60", holding_days=5 | -0.31 | 0.06 | -0.43 | -0.49 |
| `r-risk-parity-jp-growth-0001` | cost_bps=10, target_vol=0.1, base_signal="momentum_60", holding_days=5 | -0.41 | -0.04 | -0.53 | -0.57 |
| `r-risk-parity-jp-growth-0002` | cost_bps=5, target_vol=0.1, base_signal="momentum_120", holding_days=5 | -0.69 | 0.39 | -1.15 | -0.57 |
| `r-risk-parity-jp-growth-0004` | cost_bps=5, target_vol=0.1, base_signal="mean_reversion", holding_days=5 | -0.62 | -1.36 | -0.21 | -2.6 |
| `r-risk-parity-jp-growth-0018` | cost_bps=5, target_vol=0.1, base_signal="momentum_60", holding_days=60 | 0.15 | 0.72 | 0.1 | -0.85 |
| `r-risk-parity-jp-growth-0021` | cost_bps=10, target_vol=0.1, base_signal="momentum_120", holding_days=60 | -0.38 | -0.18 | -0.22 | -2.51 |
| `r-risk-parity-jp-growth-0038` | cost_bps=5, target_vol=0.1, base_signal="momentum_120", holding_days=20 | -0.45 | -0.15 | -0.4 | -2.02 |
| `r-risk-parity-jp-growth-0055` | cost_bps=10, target_vol=0.1, base_signal="momentum_60", holding_days=10 | 0 | 0.19 | 0.07 | -1.33 |
| `r-risk-parity-jp-growth-0072` | cost_bps=5, target_vol=0.1, base_signal="momentum_60", holding_days=5 | -0.57 | -0.59 | -0.59 | -0.29 |
| `r-risk-parity-jp-growth-0073` | cost_bps=10, target_vol=0.1, base_signal="momentum_60", holding_days=5 | -0.67 | -0.68 | -0.7 | -0.35 |
| `r-risk-parity-jp-growth-0083` | cost_bps=10, target_vol=0.1, base_signal="mean_reversion", holding_days=10 | -1.01 | -3.25 | -0.36 | -3.06 |
| `r-risk-parity-jp-growth-0091` | cost_bps=10, target_vol=0.1, base_signal="momentum_60", holding_days=60 | 0.11 | 0.43 | 0.08 | -0.61 |
| `r-risk-parity-jp-growth-0108` | cost_bps=5, target_vol=0.15, base_signal="momentum_60", holding_days=20 | 0.11 | 0.65 | 0.02 | -0.46 |
| `r-risk-parity-jp-growth-0125` | cost_bps=10, target_vol=0.15, base_signal="mean_reversion", holding_days=5 | -0.7 | -1.41 | -0.33 | -2.49 |
| `r-risk-parity-jp-growth-0142` | cost_bps=5, target_vol=0.15, base_signal="mean_reversion", holding_days=60 | -0.11 | -0.3 | 0.11 | -1.71 |
| `r-risk-parity-jp-growth-0159` | cost_bps=10, target_vol=0.15, base_signal="momentum_120", holding_days=20 | -0.68 | -0.45 | -0.58 | -2.38 |
| `r-risk-parity-jp-growth-0176` | cost_bps=5, target_vol=0.15, base_signal="momentum_120", holding_days=10 | -0.47 | -0.01 | -0.41 | -4.07 |
| `r-risk-parity-jp-growth-0193` | cost_bps=10, target_vol=0.2, base_signal="momentum_60", holding_days=5 | -0.41 | -0.03 | -0.53 | -0.57 |
| `r-risk-parity-jp-growth-0210` | cost_bps=5, target_vol=0.2, base_signal="momentum_60", holding_days=60 | 0.15 | 0.72 | 0.1 | -0.85 |
| `r-risk-parity-jp-growth-0227` | cost_bps=10, target_vol=0.2, base_signal="mean_reversion", holding_days=10 | -0.81 | -3.02 | -0.15 | -3.63 |
| `r-risk-parity-jp-growth-0244` | cost_bps=5, target_vol=0.2, base_signal="mean_reversion", holding_days=5 | -0.6 | -1.49 | -0.23 | -1.2 |
| `r-risk-parity-jp-growth-0261` | cost_bps=10, target_vol=0.2, base_signal="momentum_120", holding_days=60 | -0.49 | -0.59 | -0.28 | -2.93 |
| `r-risk-parity-jp-growth-0278` | cost_bps=5, target_vol=0.2, base_signal="momentum_120", holding_days=20 | -0.62 | -0.29 | -0.53 | -2.58 |
| `r-risk-parity-jp-growth-0288` | cost_bps=5, target_vol=0.3, base_signal="momentum_60", holding_days=5 | -0.3 | 0.07 | -0.42 | -0.49 |
| `r-risk-parity-jp-growth-0294` | cost_bps=5, target_vol=0.3, base_signal="momentum_60", holding_days=10 | 0.47 | 1.01 | 0.47 | -1.3 |
| `r-risk-parity-jp-growth-0297` | cost_bps=10, target_vol=0.3, base_signal="momentum_120", holding_days=10 | 0 | 0.14 | 0.09 | -4.28 |
| `r-risk-parity-jp-growth-0314` | cost_bps=5, target_vol=0.3, base_signal="momentum_120", holding_days=5 | -0.61 | 0.26 | -1.01 | 0.05 |
| `r-risk-parity-jp-growth-0331` | cost_bps=10, target_vol=0.3, base_signal="momentum_60", holding_days=60 | 0.03 | 0.18 | 0.03 | -0.51 |
| `r-risk-parity-jp-growth-0348` | cost_bps=5, target_vol=0.3, base_signal="momentum_60", holding_days=20 | -0.46 | -0.45 | -0.46 | -0.47 |
| `r-risk-parity-jp-growth-0365` | cost_bps=10, target_vol=0.3, base_signal="mean_reversion", holding_days=5 | -0.79 | -1.62 | -0.46 | -1.1 |

## 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: 0.14**
  - Value: 0.1375 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/risk-parity-jp-growth-fact-avg-corr-down

- **Average monthly return correlation with other strategies (full period): 0.00**
  - Value: 0.003 correlation
  - Context: Pairwise Pearson correlation of monthly returns across 42 strategies, full backtest period
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/risk-parity-jp-growth-fact-avg-corr-full

- **Best grid Sharpe ratio is 0.47 (p=0.34).**
  - Value: 0.47 sharpe_ratio
  - Context: period 2022-05-02–2026-06-01; cost=5bps
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/risk-parity-jp-growth-fact-best-sharpe

- **Median Sharpe across 384 grid runs is -0.45.**
  - Value: -0.45 sharpe_ratio
  - Context: Full grid of 384 parameter combinations.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/risk-parity-jp-growth-fact-median-sharpe

- **Median Sharpe in DOWN regime is -1.53 across 384 runs.**
  - Value: -1.53 sharpe_ratio
  - Context: Regime=DOWN, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/risk-parity-jp-growth-fact-regime-down

- **Median Sharpe in FLAT regime is -0.23 across 384 runs.**
  - Value: -0.23 sharpe_ratio
  - Context: Regime=FLAT, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/risk-parity-jp-growth-fact-regime-flat

- **Median Sharpe in UP regime is -0.32 across 384 runs.**
  - Value: -0.32 sharpe_ratio
  - Context: Regime=UP, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/risk-parity-jp-growth-fact-regime-up

---

Cite as: qbuntu (2026). Risk Parity / Volatility Targeting Overlay (JP Growth Stocks). https://qbuntu.ai/strategies/risk-parity-jp-growth

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