per-stock model-accuracy decomposition

3023.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	0.4797	0.3147 – 0.6167	12
Hit rate · SHORT	0.8504	0.1944 – 0.9530	6
Avg return · LONG (bps)	-57.6	-189.7 – -21.6	12
Avg return · SHORT (bps)	604.3	-216.2 – 721.7	6
Selection rate · LONG	0.0002	0.0002 – 0.0004	12
Selection rate · SHORT	0	0 – 0.0002	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

-3.1783

short

4.6633

total

1.4850

appearances 541440 · LONG 170 · SHORT 79

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