per-stock model-accuracy decomposition

3954.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	0.0476	0 – 0.4301	9
Hit rate · SHORT	0.3750	0.1870 – 0.8400	11
Avg return · LONG (bps)	-111.0	-131.3 – -20.8	9
Avg return · SHORT (bps)	-169.3	-222.6 – -37.4	11
Selection rate · LONG	0.0121	0.0006 – 0.0348	12
Selection rate · SHORT	0.0090	0.0061 – 0.0145	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

-0.7460

short

-1.7248

total

-2.4707

appearances 15360 · LONG 385 · SHORT 149

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