per-stock model-accuracy decomposition

6424.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	0.1774	0.1023 – 0.2257	12
Hit rate · SHORT	0.6092	0.4361 – 0.7912	12
Avg return · LONG (bps)	-422.1	-521.9 – -324.4	12
Avg return · SHORT (bps)	72.5	-66.7 – 286.1	12
Selection rate · LONG	0.0301	0.0254 – 0.0384	12
Selection rate · SHORT	0.0306	0.0187 – 0.0419	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

-67.7

short

10.5

total

-57.2

appearances 55296 · LONG 1671 · SHORT 1752

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