per-stock model-accuracy decomposition

4478.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	0.5563	0.5216 – 0.5719	12
Hit rate · SHORT	0.5056	0.4141 – 0.6020	12
Avg return · LONG (bps)	14.3	5.3375 – 36.0	12
Avg return · SHORT (bps)	-30.0	-113.1 – 28.3	12
Selection rate · LONG	0.0052	0.0047 – 0.0056	12
Selection rate · SHORT	0.0014	0.0007 – 0.0019	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

8.4613

short

-3.9983

total

4.4630

appearances 816384 · LONG 4211 · SHORT 1170

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