ＫｅｅＰｅｒ技研 (6036.T) quant model fit
Median hit rate and return when a model selected ＫｅｅＰｅｒ技研 (6036.T). Model: ml-factor-lgbm-9f-jp-growth. Model–stock fit, not a buy signal.
Median LONG hit rate is 0.63 (n=12). above a coin flip.Median LONG return is +256.2 bps.Above a coin flip is still 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 | 0.6303 | 0.5584 – 0.6604 | 12 |
| Hit rate · SHORT | 0.4483 | 0.0366 – 0.6000 | 9 |
| Avg return · LONG (bps) | 256.2 | 196.2 – 298.6 | 12 |
| Avg return · SHORT (bps) | -380.0 | -407.1 – -65.8 | 9 |
| Selection rate · LONG | 0.0015 | 0.0012 – 0.0017 | 12 |
| Selection rate · SHORT | 0.0001 | 0 – 0.0002 | 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%). Metrics with n = 0 are omitted.
PnL contribution
Selected LONG 1265 / SHORT 168 times out of 871,680 appearances (0.145% LONG).
sum of per-trade decimal returns across all grid combos and retrain periods (0.01 = one trade returning 1%)