per-stock model-accuracy decomposition

3077.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	0.4369	0.3728 – 0.4952	12
Hit rate · SHORT	0.4837	0.4611 – 0.5224	12
Avg return · LONG (bps)	-38.0	-57.7 – 71.0	12
Avg return · SHORT (bps)	264.7	155.0 – 295.0	12
Selection rate · LONG	0.0218	0.0193 – 0.0265	12
Selection rate · SHORT	0.0693	0.0571 – 0.0758	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

-1.4344

short

217.7

total

216.2

appearances 138240 · LONG 3142 · SHORT 9302

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