per-stock model-accuracy decomposition

7670.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	0.4737	0.4124 – 0.5715	12
Hit rate · SHORT	0.5108	0.3136 – 0.5919	12
Avg return · LONG (bps)	-57.6	-116.4 – -19.9	12
Avg return · SHORT (bps)	-8.8883	-204.9 – 118.4	12
Selection rate · LONG	0.0039	0.0029 – 0.0119	12
Selection rate · SHORT	0.0158	0.0121 – 0.0217	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

-3.5954

short

-6.3500

total

-9.9455

appearances 94464 · LONG 739 · SHORT 1530

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