per-stock model-accuracy decomposition

3634.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	0.2151	0.1757 – 0.2896	12
Hit rate · SHORT	0.9925	0.9338 – 1	12
Avg return · LONG (bps)	-51.5	-84.1 – -41.9	12
Avg return · SHORT (bps)	1202.9	1049.0 – 1387.5	12
Selection rate · LONG	0.0162	0.0124 – 0.0236	12
Selection rate · SHORT	0.0202	0.0150 – 0.0227	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

-6.1370

short

158.9

total

152.7

appearances 72192 · LONG 1389 · SHORT 1375

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