per-stock model-accuracy decomposition

3929.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	0.3489	0.2976 – 0.3685	12
Hit rate · SHORT	0.7982	0.7480 – 0.8404	12
Avg return · LONG (bps)	74.1	-91.4 – 145.5	12
Avg return · SHORT (bps)	427.9	404.9 – 506.4	12
Selection rate · LONG	0.0166	0.0130 – 0.0203	12
Selection rate · SHORT	0.0342	0.0320 – 0.0375	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

18.9

short

299.9

total

318.7

appearances 188160 · LONG 3286 · SHORT 6367

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