per-stock model-accuracy decomposition

3648.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	0.2942	0.2356 – 0.3352	12
Hit rate · SHORT	0.7446	0.6753 – 0.7793	12
Avg return · LONG (bps)	-165.3	-352.0 – -128.5	12
Avg return · SHORT (bps)	-189.0	-396.9 – 21.0	12
Selection rate · LONG	0.0073	0.0056 – 0.0091	12
Selection rate · SHORT	0.0107	0.0079 – 0.0121	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

-32.8

short

-36.7

total

-69.5

appearances 195072 · LONG 1482 · SHORT 2048

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