per-stock model-accuracy decomposition

4293.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	0.2213	0.0910 – 0.3831	12
Hit rate · SHORT	0.0774	0 – 0.4937	12
Avg return · LONG (bps)	-67.8	-116.4 – 33.4	12
Avg return · SHORT (bps)	-317.7	-348.4 – -63.4	12
Selection rate · LONG	0.0005	0.0003 – 0.0007	12
Selection rate · SHORT	0.0003	0.0002 – 0.0004	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

-1.9807

short

-4.4099

total

-6.3905

appearances 772608 · LONG 382 · SHORT 217

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