per-stock model-accuracy decomposition

4374.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	0.1991	0.1617 – 0.3015	12
Hit rate · SHORT	0.7833	0.7179 – 0.8145	12
Avg return · LONG (bps)	-233.9	-328.7 – -155.1	12
Avg return · SHORT (bps)	135.5	83.4 – 147.4	12
Selection rate · LONG	0.0049	0.0040 – 0.0052	12
Selection rate · SHORT	0.0029	0.0024 – 0.0030	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

-56.9

short

13.7

total

-43.1

appearances 521472 · LONG 2557 · SHORT 1425

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