per-stock model-accuracy decomposition

4389.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	0.2385	0.1530 – 0.2832	12
Hit rate · SHORT	0.0837	0.0530 – 0.3214	12
Avg return · LONG (bps)	-27.1	-79.3 – -11.2	12
Avg return · SHORT (bps)	-136.9	-249.5 – -53.0	12
Selection rate · LONG	0.0111	0.0108 – 0.0119	12
Selection rate · SHORT	0.0060	0.0021 – 0.0066	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

-1.7003

short

-11.2

total

-12.9

appearances 119040 · LONG 1263 · SHORT 573

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