# 海帆 (3133.T) — per-stock model accuracy

> Model predictability decomposition: measures how accurately the ml-factor-lgbm-9f-jp-growth model family predicts this stock's returns within the jp-listed universe. High hit_rate_long does NOT mean 'good stock to buy' -- it means 'the model historically predicted this stock well when selecting it LONG'. This is a property of model-stock fit, not intrinsic stock quality.

- **Name**: 海帆
- **Sector**: 小売
- **Universe**: jp-listed
- **Decomposes**: `ml-factor-lgbm-9f-jp-growth` (strategy verdict: marginal) — https://qbuntu.ai/strategies/ml-factor-lgbm-9f-jp-growth
- **Computed asof**: 2026-10-01T02:33:09
- **HTML**: https://qbuntu.ai/stocks/3133.T
- **JSON**: https://qbuntu.ai/v1/stocks/3133.T
- **License**: CC-BY-4.0

## Accuracy (median across grid)

Median LONG hit rate is 0.4785 — near a coin flip.

| metric | median | p25 | p75 | n |
|---|---:|---:|---:|---:|
| hit_rate_long | 0.4785 | 0.4715 | 0.5381 | 12 |
| hit_rate_short | 0.5010 | 0.4761 | 0.5430 | 12 |
| avg_return_long_bps | -36.2 | -62.3 | 3.9695 | 12 |
| avg_return_short_bps | -26.1 | -119.8 | 26.3 | 12 |
| selection_rate_long | 0.0144 | 0.0139 | 0.0159 | 12 |
| selection_rate_short | 0.0258 | 0.0241 | 0.0273 | 12 |

Hit rate ≈ 0.5 means the model's picks on this stock were near coin-flip. Returns in bps/trade. Metrics with n = 0 are omitted; n < 5 is a thin sample.

## PnL contribution

- long: -30.0
- short: -111.4
- total: -141.3
- appearances: LONG 10825 / SHORT 19061 of 735744

---

Research, not investment advice. These metrics describe model–stock fit, not the stock's merit.
Cite as: qbuntu (2026). 3133.T per-stock accuracy. https://qbuntu.ai/stocks/3133.T