# Skewness Reversal (US S&P 500)

- **Slug**: `skewness-reversal-us-sp500`
- **Verdict**: rejected (no_edge)
- **Asset class**: equity
- **Categories**: factor, reversal, skewness
- **Source**: qbuntu-analysis (computed asof 2026-08-02T16:26:49)
- **Reproducibility**: analysis-engine@2f23bb7, backtest-lib@711b855, grid tier=shallow (python 3.10.11, numpy 2.2.6, pandas 2.3.3)
- **HTML**: https://qbuntu.ai/strategies/skewness-reversal-us-sp500
- **JSON**: https://qbuntu.ai/v1/strategies/skewness-reversal-us-sp500
- **License**: CC-BY-4.0

## Hypothesis

Investors overpay for lottery-like positive skewness and shun negative skewness (Harvey & Siddique 2000 line): stocks with extreme recent return skewness should subsequently revert. Ranking on realized skewness tests the effect long/short.

## Why it didn't work

Across 144 grid combinations, median Sharpe=-1.09, best=0.46. Primary failure mode: no_edge.

## Performance summary

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

| Metric | Value |
|---|---|
| Sharpe (median) | -1.0884 |
| Max drawdown | -18.5% |
| p-value | 0.025 |
| Backtest period | 2022-02-01 to 2026-06-01 |

Sharpe distribution across 144 grid runs: median -1.09, best 0.46 (best-case — not representative), worst -3.3, p25 -1.56, p75 -0.55.

## 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: GSPC SMA20/SMA60 three-class
- Transaction cost bps: 5

## Target universe

S&P 500 constituents, ~503 stocks

## Runs (30)

| run_id | params | sharpe | UP | FLAT | DOWN |
|---|---|---:|---:|---:|---:|
| `r-skewness-reversal-us-sp500-0000` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=1 | -1.94 | -2.64 | -1.87 | -0.83 |
| `r-skewness-reversal-us-sp500-0001` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=5 | -1.37 | -1.51 | -1.74 | 0.06 |
| `r-skewness-reversal-us-sp500-0002` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=20 | -0.35 | -1.32 | -0.12 | 1.63 |
| `r-skewness-reversal-us-sp500-0003` | cost_bps=5, n_stocks=5, regime_gate=true, holding_days=1 | -1.57 | -1.93 | -1.87 | -0.83 |
| `r-skewness-reversal-us-sp500-0006` | cost_bps=10, n_stocks=5, regime_gate=false, holding_days=1 | -2.34 | -3.12 | -2.24 | -1.15 |
| `r-skewness-reversal-us-sp500-0010` | cost_bps=10, n_stocks=5, regime_gate=true, holding_days=5 | -1.25 | -1.2 | -1.88 | -0.24 |
| `r-skewness-reversal-us-sp500-0016` | cost_bps=5, n_stocks=10, regime_gate=true, holding_days=5 | -0.7 | -0.61 | -1.26 | 0.33 |
| `r-skewness-reversal-us-sp500-0022` | cost_bps=10, n_stocks=10, regime_gate=true, holding_days=5 | -0.94 | -0.81 | -1.52 | -0.02 |
| `r-skewness-reversal-us-sp500-0028` | cost_bps=5, n_stocks=20, regime_gate=true, holding_days=5 | -0.4 | 0.36 | -1.75 | 0.64 |
| `r-skewness-reversal-us-sp500-0034` | cost_bps=10, n_stocks=20, regime_gate=true, holding_days=5 | -0.69 | 0.16 | -2.1 | -0.11 |
| `r-skewness-reversal-us-sp500-0036` | cost_bps=5, n_stocks=50, regime_gate=false, holding_days=1 | -1.42 | -1.8 | -1.33 | -0.31 |
| `r-skewness-reversal-us-sp500-0041` | cost_bps=5, n_stocks=50, regime_gate=true, holding_days=20 | 0.32 | 0.68 | -0.84 | 1.45 |
| `r-skewness-reversal-us-sp500-0047` | cost_bps=10, n_stocks=50, regime_gate=true, holding_days=20 | 0.15 | 0.58 | -1.09 | 1.11 |
| `r-skewness-reversal-us-sp500-0053` | cost_bps=5, n_stocks=5, regime_gate=true, holding_days=20 | 0.04 | 0.33 | -1.1 | 1.64 |
| `r-skewness-reversal-us-sp500-0059` | cost_bps=10, n_stocks=5, regime_gate=true, holding_days=20 | -0.05 | 0.26 | -1.21 | 1.52 |
| `r-skewness-reversal-us-sp500-0065` | cost_bps=5, n_stocks=10, regime_gate=true, holding_days=20 | -0.18 | -0.05 | -1.65 | 1.74 |
| `r-skewness-reversal-us-sp500-0071` | cost_bps=10, n_stocks=10, regime_gate=true, holding_days=20 | -0.3 | -0.13 | -1.82 | 1.58 |
| `r-skewness-reversal-us-sp500-0077` | cost_bps=5, n_stocks=20, regime_gate=true, holding_days=20 | -0.68 | -0.17 | -1.61 | 0 |
| `r-skewness-reversal-us-sp500-0078` | cost_bps=10, n_stocks=20, regime_gate=false, holding_days=1 | -3.3 | -4.12 | -2.22 | -3.46 |
| `r-skewness-reversal-us-sp500-0084` | cost_bps=5, n_stocks=50, regime_gate=false, holding_days=1 | -2.24 | -3.07 | -1.46 | -1.73 |
| `r-skewness-reversal-us-sp500-0090` | cost_bps=10, n_stocks=50, regime_gate=false, holding_days=1 | -3.06 | -3.96 | -2.18 | -2.54 |
| `r-skewness-reversal-us-sp500-0096` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=1 | -1.46 | -1.66 | -1.48 | -0.93 |
| `r-skewness-reversal-us-sp500-0097` | cost_bps=5, n_stocks=5, regime_gate=false, holding_days=5 | -1.12 | -0.68 | -1.42 | -1.47 |
| `r-skewness-reversal-us-sp500-0101` | cost_bps=5, n_stocks=5, regime_gate=true, holding_days=20 | 0.46 | 0.71 | -0.03 | 0.91 |
| `r-skewness-reversal-us-sp500-0104` | cost_bps=10, n_stocks=5, regime_gate=false, holding_days=20 | 0.33 | 0.55 | -0.14 | 0.81 |
| `r-skewness-reversal-us-sp500-0110` | cost_bps=5, n_stocks=10, regime_gate=false, holding_days=20 | -0.66 | -1.32 | -0.57 | 0.9 |
| `r-skewness-reversal-us-sp500-0116` | cost_bps=10, n_stocks=10, regime_gate=false, holding_days=20 | -0.8 | -1.47 | -0.7 | 0.76 |
| `r-skewness-reversal-us-sp500-0122` | cost_bps=5, n_stocks=20, regime_gate=false, holding_days=20 | -0.76 | -1.3 | -0.55 | 0.48 |
| `r-skewness-reversal-us-sp500-0128` | cost_bps=10, n_stocks=20, regime_gate=false, holding_days=20 | -0.95 | -1.48 | -0.72 | 0.27 |
| `r-skewness-reversal-us-sp500-0134` | cost_bps=5, n_stocks=50, regime_gate=false, holding_days=20 | -1.02 | -1.59 | -0.63 | 0.02 |

## Facts (5)

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

- **Best grid Sharpe ratio is 0.46 (p=0.34).**
  - Value: 0.46 sharpe_ratio
  - Context: period 2022-02-01–2026-06-01; cost=5bps
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/skewness-reversal-us-sp500-fact-best-sharpe

- **Median Sharpe across 144 grid runs is -1.09.**
  - Value: -1.09 sharpe_ratio
  - Context: Full grid of 144 parameter combinations.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/skewness-reversal-us-sp500-fact-median-sharpe

- **Median Sharpe in DOWN regime is -0.24 across 144 runs.**
  - Value: -0.24 sharpe_ratio
  - Context: Regime=DOWN, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/skewness-reversal-us-sp500-fact-regime-down

- **Median Sharpe in FLAT regime is -1.59 across 144 runs.**
  - Value: -1.59 sharpe_ratio
  - Context: Regime=FLAT, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/skewness-reversal-us-sp500-fact-regime-flat

- **Median Sharpe in UP regime is -1.16 across 144 runs.**
  - Value: -1.16 sharpe_ratio
  - Context: Regime=UP, N225 SMA20/SMA60 classification.
  - Supports verdict: `rejected`
  - Cite: https://qbuntu.ai/cite/skewness-reversal-us-sp500-fact-regime-up

## Related strategies

- same_strategy: [skewness-reversal-jp-all](https://qbuntu.ai/strategies/skewness-reversal-jp-all)
- same_strategy: [skewness-reversal-jp-growth](https://qbuntu.ai/strategies/skewness-reversal-jp-growth)

---

Cite as: qbuntu (2026). Skewness Reversal (US S&P 500). https://qbuntu.ai/strategies/skewness-reversal-us-sp500

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