per-stock model-accuracy decomposition

3810.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	0.3594	0.3090 – 0.3833	12
Hit rate · SHORT	0.5233	0.4757 – 0.5389	12
Avg return · LONG (bps)	-44.1	-98.3 – -13.6	12
Avg return · SHORT (bps)	-138.9	-204.9 – -81.9	12
Selection rate · LONG	0.0142	0.0127 – 0.0158	12
Selection rate · SHORT	0.0216	0.0209 – 0.0231	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

-55.4

short

-233.8

total

-289.2

appearances 678144 · LONG 9194 · SHORT 14836

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