per-stock model-accuracy decomposition

1514.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	0.4427	0.4124 – 0.4632	12
Hit rate · SHORT	0.6671	0.6400 – 0.7076	12
Avg return · LONG (bps)	46.1	-39.1 – 102.3	12
Avg return · SHORT (bps)	197.3	27.3 – 265.4	12
Selection rate · LONG	0.0171	0.0160 – 0.0194	12
Selection rate · SHORT	0.0157	0.0148 – 0.0165	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

45.3

short

169.2

total

214.5

appearances 772608 · LONG 13895 · SHORT 12127

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