per-stock model-accuracy decomposition

3624.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	0.3406	0.3203 – 0.3671	12
Hit rate · SHORT	0.4934	0.4292 – 0.6052	12
Avg return · LONG (bps)	-19.9	-50.3 – 15.6	12
Avg return · SHORT (bps)	51.6	-89.1 – 183.8	12
Selection rate · LONG	0.0191	0.0135 – 0.0244	12
Selection rate · SHORT	0.0166	0.0149 – 0.0176	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

-13.9

short

65.7

total

51.8

appearances 532224 · LONG 9860 · SHORT 8822

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