# 赤阪鐵工所 (6022.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**: 赤阪鐵工所
- **Sector**: 機械
- **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/6022.T
- **JSON**: https://qbuntu.ai/v1/stocks/6022.T
- **License**: CC-BY-4.0

## Accuracy (median across grid)

Median LONG hit rate is 0.5298 — near a coin flip.

| metric | median | p25 | p75 | n |
|---|---:|---:|---:|---:|
| hit_rate_long | 0.5298 | 0.4635 | 0.5868 | 12 |
| hit_rate_short | 0.8147 | 0.7772 | 0.8617 | 12 |
| avg_return_long_bps | 6.0410 | -121.0 | 121.7 | 12 |
| avg_return_short_bps | 308.2 | 257.0 | 355.4 | 12 |
| selection_rate_long | 0.0163 | 0.0122 | 0.0176 | 12 |
| selection_rate_short | 0.0232 | 0.0228 | 0.0239 | 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: 2.6623
- short: 106.2
- total: 108.9
- appearances: LONG 2267 / SHORT 3431 of 146688

---

Research, not investment advice. These metrics describe model–stock fit, not the stock's merit.
Cite as: qbuntu (2026). 6022.T per-stock accuracy. https://qbuntu.ai/stocks/6022.T