per-stock model-accuracy decomposition

6836.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	0.4968	0.4776 – 0.5124	12
Hit rate · SHORT	0.5974	0.5738 – 0.6173	12
Avg return · LONG (bps)	17.1	-31.3 – 68.9	12
Avg return · SHORT (bps)	89.1	11.9 – 122.8	12
Selection rate · LONG	0.0483	0.0468 – 0.0516	12
Selection rate · SHORT	0.0502	0.0443 – 0.0519	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

14.1

short

139.0

total

153.1

appearances 378624 · LONG 18496 · SHORT 18281

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