per-stock model-accuracy decomposition

2926.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	0.3553	0.1992 – 0.4280	12
Hit rate · SHORT	0.2170	0.1238 – 0.3395	12
Avg return · LONG (bps)	206.6	-124.7 – 412.7	12
Avg return · SHORT (bps)	-309.0	-457.2 – -0.7053	12
Selection rate · LONG	0.0029	0.0022 – 0.0038	12
Selection rate · SHORT	0.0070	0.0051 – 0.0112	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

7.7228

short

-18.9

total

-11.2

appearances 132096 · LONG 418 · SHORT 1008

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