per-stock model-accuracy decomposition

5527.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	0.5800	0.5253 – 0.6702	12
Hit rate · SHORT	0.3056	0.1125 – 0.4333	10
Avg return · LONG (bps)	113.2	41.1 – 195.7	12
Avg return · SHORT (bps)	-33.9	-91.1 – 112.0	10
Selection rate · LONG	0.0054	0.0035 – 0.0069	12
Selection rate · SHORT	0.0002	0.0001 – 0.0004	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

15.6

short

-0.3415

total

15.3

appearances 316608 · LONG 1698 · SHORT 93

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