per-stock model-accuracy decomposition

4761.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	0.5838	0.4186 – 0.7005	12
Hit rate · SHORT	0.7795	0.7153 – 0.8241	12
Avg return · LONG (bps)	187.0	-69.7 – 418.9	12
Avg return · SHORT (bps)	131.3	48.6 – 342.8	12
Selection rate · LONG	0.0110	0.0095 – 0.0170	12
Selection rate · SHORT	0.0217	0.0180 – 0.0258	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

36.3

short

42.3

total

78.6

appearances 148224 · LONG 1960 · SHORT 3218

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