per-stock model-accuracy decomposition

6635.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.

Decomposes ml-factor-lgbm-9f-jp-growth. Standalone walk-forward run of the same LightGBM 9-factor family on the jp-listed universe (~4,100 tickers); the referenced record's verdict applies to the jp-growth universe only.

Accuracy (median across grid)

metric	median	p25 – p75	n
Hit rate · LONG	0.3420	0.1686 – 0.5977	12
Hit rate · SHORT	0.5710	0.3423 – 0.8275	12
Avg return · LONG (bps)	-94.3	-212.3 – 0.8469	12
Avg return · SHORT (bps)	214.8	-153.0 – 733.9	12
Selection rate · LONG	0.0069	0.0051 – 0.0078	12
Selection rate · SHORT	0.0079	0.0038 – 0.0091	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

-8.6540

short

25.0

total

16.4

appearances 108288 · LONG 667 · SHORT 784

Research, not investment advice. Metrics describe model–stock fit, not the stock's merit.