per-stock model-accuracy decomposition

8912.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	0.5388	0.4525 – 0.5652	12
Hit rate · SHORT	0.6446	0.6070 – 0.7271	12
Avg return · LONG (bps)	-58.5	-85.7 – -14.8	12
Avg return · SHORT (bps)	281.9	200.4 – 455.7	12
Selection rate · LONG	0.0094	0.0073 – 0.0130	12
Selection rate · SHORT	0.0254	0.0227 – 0.0288	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

-4.2788

short

75.8

total

71.5

appearances 96000 · LONG 1011 · SHORT 2595

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