per-stock model-accuracy decomposition

3512.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	0.6250	0.4545 – 0.8400	9
Hit rate · SHORT	0.4643	0.1603 – 0.5952	12
Avg return · LONG (bps)	773.5	348.0 – 1087.2	9
Avg return · SHORT (bps)	-16.8	-178.3 – 125.2	12
Selection rate · LONG	0.0069	0.0021 – 0.0134	12
Selection rate · SHORT	0.0083	0.0058 – 0.0137	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

16.7

short

-2.4205

total

14.2

appearances 25344 · LONG 208 · SHORT 248

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