# 新東 (5380.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**: 新東
- **Sector**: 建設・資材
- **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/5380.T
- **JSON**: https://qbuntu.ai/v1/stocks/5380.T
- **License**: CC-BY-4.0

## Accuracy (median across grid)

Median LONG hit rate is 0.2364 — below a coin flip.

| metric | median | p25 | p75 | n |
|---|---:|---:|---:|---:|
| hit_rate_long | 0.2364 | 0.2109 | 0.2766 | 12 |
| hit_rate_short | 0.4071 | 0.3449 | 0.4380 | 12 |
| avg_return_long_bps | -160.2 | -229.2 | -117.3 | 12 |
| avg_return_short_bps | 109.2 | -9.8050 | 201.3 | 12 |
| selection_rate_long | 0.0470 | 0.0256 | 0.0626 | 12 |
| selection_rate_short | 0.0476 | 0.0453 | 0.0694 | 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: -110.1
- short: 73.3
- total: -36.8
- appearances: LONG 6665 / SHORT 7640 of 140544

---

Research, not investment advice. These metrics describe model–stock fit, not the stock's merit.
Cite as: qbuntu (2026). 5380.T per-stock accuracy. https://qbuntu.ai/stocks/5380.T