per-stock model-accuracy decomposition

4475.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	0.4313	0.4005 – 0.4706	12
Hit rate · SHORT	0.6332	0.5568 – 0.7777	12
Avg return · LONG (bps)	-73.2	-102.1 – -50.5	12
Avg return · SHORT (bps)	-17.0	-56.6 – 87.4	12
Selection rate · LONG	0.0079	0.0054 – 0.0091	12
Selection rate · SHORT	0.0071	0.0067 – 0.0082	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

-51.4

short

11.0

total

-40.4

appearances 816384 · LONG 6397 · SHORT 6028

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