per-stock model-accuracy decomposition

6786.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	0.3607	0.3291 – 0.4234	12
Hit rate · SHORT	0.5136	0.4856 – 0.5706	12
Avg return · LONG (bps)	-74.7	-120.8 – -3.0312	12
Avg return · SHORT (bps)	-14.3	-142.7 – 117.9	12
Selection rate · LONG	0.0382	0.0338 – 0.0440	12
Selection rate · SHORT	0.0700	0.0635 – 0.0741	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

-34.1

short

-15.3

total

-49.4

appearances 116736 · LONG 4533 · SHORT 8124

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