per-stock model-accuracy decomposition

6557.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	0.5419	0.4597 – 0.5799	12
Hit rate · SHORT	0.6214	0.5926 – 0.6381	12
Avg return · LONG (bps)	-2.8191	-42.7 – 85.3	12
Avg return · SHORT (bps)	257.4	217.9 – 367.7	12
Selection rate · LONG	0.0152	0.0121 – 0.0201	12
Selection rate · SHORT	0.0181	0.0160 – 0.0192	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

22.4

short

178.9

total

201.3

appearances 347136 · LONG 5851 · SHORT 6100

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