# 総医研ホールディングス (2385.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**: 総医研ホールディングス
- **Sector**: 情報通信・サービスその他
- **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/2385.T
- **JSON**: https://qbuntu.ai/v1/stocks/2385.T
- **License**: CC-BY-4.0

## Accuracy (median across grid)

Median LONG hit rate is 0.1948 — below a coin flip.

| metric | median | p25 | p75 | n |
|---|---:|---:|---:|---:|
| hit_rate_long | 0.1948 | 0.1104 | 0.2975 | 12 |
| hit_rate_short | 0.7127 | 0.6556 | 0.8120 | 12 |
| avg_return_long_bps | -159.1 | -191.2 | -110.1 | 12 |
| avg_return_short_bps | 74.5 | 6.9184 | 149.0 | 12 |
| selection_rate_long | 0.0027 | 0.0017 | 0.0033 | 12 |
| selection_rate_short | 0.0072 | 0.0044 | 0.0094 | 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: -10.6
- short: 12.5
- total: 1.8791
- appearances: LONG 737 / SHORT 1923 of 290304

---

Research, not investment advice. These metrics describe model–stock fit, not the stock's merit.
Cite as: qbuntu (2026). 2385.T per-stock accuracy. https://qbuntu.ai/stocks/2385.T