per-stock model-accuracy decomposition

9254.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	0.5769	0.5437 – 0.6358	12
Hit rate · SHORT	0.5755	0.5559 – 0.6101	12
Avg return · LONG (bps)	18.5	-104.8 – 141.7	12
Avg return · SHORT (bps)	-167.3	-267.4 – -84.4	12
Selection rate · LONG	0.0243	0.0210 – 0.0297	12
Selection rate · SHORT	0.0294	0.0290 – 0.0317	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

11.4

short

-89.5

total

-78.1

appearances 165312 · LONG 4090 · SHORT 4968

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