per-stock model-accuracy decomposition

5856.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	0.1980	0.1624 – 0.2902	12
Hit rate · SHORT	0.7637	0.6834 – 0.7876	12
Avg return · LONG (bps)	-64.1	-164.2 – 38.6	12
Avg return · SHORT (bps)	494.0	441.0 – 519.5	12
Selection rate · LONG	0.0334	0.0274 – 0.0473	12
Selection rate · SHORT	0.0214	0.0181 – 0.0229	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

-25.5

short

142.0

total

116.5

appearances 144384 · LONG 5237 · SHORT 3020

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