per-stock model-accuracy decomposition
5259.T
computed asof 2026-08-07T09:15:22
read this first — not a buy signal
Model predictability decomposition: measures how accurately the ml-factor-lgbm-9f-jp-growth model family predicts this stock's returns within the jp-growth 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.
Accuracy (median across grid)
| metric | median | p25 – p75 | n |
|---|---|---|---|
| Hit rate · LONG | 0.4343 | 0.3787 – 0.4739 | 12 |
| Hit rate · SHORT | 0.5562 | 0.4778 – 0.5618 | 12 |
| Avg return · LONG (bps) | -23.2 | -67.0 – 18.3 | 12 |
| Avg return · SHORT (bps) | 77.8 | 66.9 – 102.5 | 12 |
| Selection rate · LONG | 0.0267 | 0.0107 – 0.0293 | 12 |
| Selection rate · SHORT | 0.0263 | 0.0235 – 0.0301 | 12 |
Hit rate ≈ 0.5 means the model's picks on this stock were near coin-flip. Returns in bps per trade (1 bps = 0.01%).
PnL contribution
long
-6.6294
short
43.6
total
36.9
appearances 188160 · LONG 4202 · SHORT 5140