per-stock model-accuracy decomposition

9073.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	0.4008	0.3552 – 0.6092	12
Hit rate · SHORT	0.6065	0.5941 – 0.6266	12
Avg return · LONG (bps)	55.9	28.0 – 82.3	12
Avg return · SHORT (bps)	-129.5	-158.3 – -60.1	12
Selection rate · LONG	0.0640	0.0482 – 0.0664	12
Selection rate · SHORT	0.0973	0.0882 – 0.1065	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

16.6

short

-35.5

total

-18.9

appearances 40704 · LONG 2531 · SHORT 3938

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