per-stock model-accuracy decomposition

2321.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	0.3684	0.3356 – 0.3902	12
Hit rate · SHORT	0.6504	0.6256 – 0.6990	12
Avg return · LONG (bps)	-59.4	-81.4 – 16.3	12
Avg return · SHORT (bps)	-165.5	-299.1 – -10.7	12
Selection rate · LONG	0.0156	0.0142 – 0.0228	12
Selection rate · SHORT	0.0207	0.0190 – 0.0234	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

-29.4

short

-111.1

total

-140.5

appearances 372480 · LONG 6473 · SHORT 7835

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