per-stock model-accuracy decomposition

2158.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	0.3961	0.3731 – 0.4308	12
Hit rate · SHORT	0.5599	0.4896 – 0.5927	12
Avg return · LONG (bps)	15.7	-21.5 – 41.7	12
Avg return · SHORT (bps)	50.1	-76.1 – 82.2	12
Selection rate · LONG	0.0052	0.0047 – 0.0057	12
Selection rate · SHORT	0.0037	0.0032 – 0.0048	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

1.2456

short

1.7616

total

3.0072

appearances 817152 · LONG 4192 · SHORT 3213

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