per-stock model-accuracy decomposition

3727.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	0.2480	0.2094 – 0.2931	12
Hit rate · SHORT	0.8471	0.7875 – 0.8906	12
Avg return · LONG (bps)	-150.8	-331.0 – -142.0	12
Avg return · SHORT (bps)	403.9	278.4 – 435.1	12
Selection rate · LONG	0.0101	0.0087 – 0.0128	12
Selection rate · SHORT	0.0145	0.0125 – 0.0153	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

-50.5

short

106.7

total

56.2

appearances 219648 · LONG 2398 · SHORT 3058

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