per-stock model-accuracy decomposition

3858.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	0.2890	0.1885 – 0.4100	12
Hit rate · SHORT	0.5376	0.4748 – 0.6256	12
Avg return · LONG (bps)	-180.7	-243.1 – -132.4	12
Avg return · SHORT (bps)	-72.6	-196.5 – 111.7	12
Selection rate · LONG	0.0073	0.0059 – 0.0083	12
Selection rate · SHORT	0.0149	0.0129 – 0.0168	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

-41.6

short

-9.0589

total

-50.6

appearances 281088 · LONG 2097 · SHORT 4015

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