per-stock model-accuracy decomposition
3021.T
computed asof 2026-08-07T09:15:52
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-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.
Accuracy (median across grid)
| metric | median | p25 – p75 | n |
|---|---|---|---|
| Hit rate · LONG | 0.2182 | 0.1212 – 0.3185 | 12 |
| Hit rate · SHORT | 1 | 1 – 1 | 3 |
| Avg return · LONG (bps) | -147.1 | -212.6 – -92.9 | 12 |
| Avg return · SHORT (bps) | 376.1 | 342.5 – 376.1 | 3 |
| Selection rate · LONG | 0.0055 | 0.0044 – 0.0067 | 12 |
| Selection rate · SHORT | 0 | 0 – 0 | 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
-12.1
short
0.1061
total
-12.0
appearances 130560 · LONG 832 · SHORT 3