per-stock model-accuracy decomposition

4107.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	0.4504	0.4227 – 0.5244	12
Hit rate · SHORT	0.7956	0.6572 – 0.8908	12
Avg return · LONG (bps)	7.4601	-18.2 – 70.6	12
Avg return · SHORT (bps)	396.0	225.6 – 527.4	12
Selection rate · LONG	0.0142	0.0124 – 0.0154	12
Selection rate · SHORT	0.0050	0.0039 – 0.0053	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

25.0

short

113.7

total

138.7

appearances 662016 · LONG 9162 · SHORT 3170

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