per-stock model-accuracy decomposition

3686.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	0.2509	0.2247 – 0.2823	12
Hit rate · SHORT	0.5290	0.4910 – 0.6589	12
Avg return · LONG (bps)	-192.6	-254.4 – -108.0	12
Avg return · SHORT (bps)	160.1	88.8 – 402.9	12
Selection rate · LONG	0.0066	0.0059 – 0.0076	12
Selection rate · SHORT	0.0034	0.0029 – 0.0042	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

-84.3

short

50.3

total

-34.0

appearances 623616 · LONG 4361 · SHORT 2143

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