# テクニスコ (2962.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**: テクニスコ
- **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/2962.T
- **JSON**: https://qbuntu.ai/v1/stocks/2962.T
- **License**: CC-BY-4.0

## Accuracy (median across grid)

Median LONG hit rate is 0.4128 — below a coin flip.

| metric | median | p25 | p75 | n |
|---|---:|---:|---:|---:|
| hit_rate_long | 0.4128 | 0.3558 | 0.4824 | 12 |
| hit_rate_short | 0.5580 | 0.5051 | 0.5858 | 12 |
| avg_return_long_bps | -58.9 | -117.8 | 54.1 | 12 |
| avg_return_short_bps | 242.0 | 198.8 | 331.0 | 12 |
| selection_rate_long | 0.0183 | 0.0154 | 0.0221 | 12 |
| selection_rate_short | 0.0405 | 0.0383 | 0.0414 | 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: -27.0
- short: 380.4
- total: 353.4
- appearances: LONG 6935 / SHORT 14641 of 364992

---

Research, not investment advice. These metrics describe model–stock fit, not the stock's merit.
Cite as: qbuntu (2026). 2962.T per-stock accuracy. https://qbuntu.ai/stocks/2962.T