per-stock model-accuracy decomposition

3521.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	0.6174	0.3404 – 0.6600	12
Hit rate · SHORT	0.7064	0.5258 – 0.8964	12
Avg return · LONG (bps)	14.8	-51.4 – 96.4	12
Avg return · SHORT (bps)	16.6	-221.2 – 227.9	12
Selection rate · LONG	0.0079	0.0046 – 0.0140	12
Selection rate · SHORT	0.0126	0.0098 – 0.0136	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

-0.0260

short

-2.9433

total

-2.9693

appearances 119808 · LONG 1263 · SHORT 1465

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