per-stock model-accuracy decomposition

9241.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	0.4179	0.3349 – 0.4815	12
Hit rate · SHORT	0.5656	0.5518 – 0.6236	12
Avg return · LONG (bps)	-54.5	-190.0 – 15.9	12
Avg return · SHORT (bps)	508.7	368.6 – 619.6	12
Selection rate · LONG	0.0256	0.0214 – 0.0326	12
Selection rate · SHORT	0.0409	0.0356 – 0.0447	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

-33.9

short

259.8

total

225.9

appearances 131328 · LONG 3685 · SHORT 5433

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