# 神栄 (3004.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**: 神栄
- **Sector**: 商社・卸売
- **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/3004.T
- **JSON**: https://qbuntu.ai/v1/stocks/3004.T
- **License**: CC-BY-4.0

## Accuracy (median across grid)

Median LONG hit rate is 0.4500 — near a coin flip.

| metric | median | p25 | p75 | n |
|---|---:|---:|---:|---:|
| hit_rate_long | 0.4500 | 0.4023 | 0.5229 | 12 |
| hit_rate_short | 0.8065 | 0.7060 | 0.8990 | 11 |
| avg_return_long_bps | 112.6 | 23.6 | 149.3 | 12 |
| avg_return_short_bps | 91.3 | -9.1044 | 344.2 | 11 |
| selection_rate_long | 0.0068 | 0.0033 | 0.0076 | 12 |
| selection_rate_short | 0.0007 | 0.0005 | 0.0022 | 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: 13.3
- short: 9.2126
- total: 22.5
- appearances: LONG 1166 / SHORT 340 of 203520

---

Research, not investment advice. These metrics describe model–stock fit, not the stock's merit.
Cite as: qbuntu (2026). 3004.T per-stock accuracy. https://qbuntu.ai/stocks/3004.T