per-stock model-accuracy decomposition

9553.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	0.4264	0.3843 – 0.4452	12
Hit rate · SHORT	0.7015	0.6418 – 0.7421	12
Avg return · LONG (bps)	-46.3	-76.3 – -3.5838	12
Avg return · SHORT (bps)	88.5	45.8 – 147.8	12
Selection rate · LONG	0.0130	0.0119 – 0.0149	12
Selection rate · SHORT	0.0104	0.0076 – 0.0112	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

-41.2

short

57.2

total

16.1

appearances 698304 · LONG 9254 · SHORT 6710

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