per-stock model-accuracy decomposition

4664.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	0.1701	0.0756 – 0.2684	12
Hit rate · SHORT	0.3087	0.2878 – 0.3408	12
Avg return · LONG (bps)	-569.6	-920.7 – -185.8	12
Avg return · SHORT (bps)	-113.4	-195.3 – -4.1133	12
Selection rate · LONG	0.0221	0.0176 – 0.0245	12
Selection rate · SHORT	0.0994	0.0962 – 0.1073	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

-128.2

short

-89.5

total

-217.7

appearances 90624 · LONG 1957 · SHORT 9192

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