per-stock model-accuracy decomposition

6574.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	0.4113	0.3926 – 0.4320	12
Hit rate · SHORT	0.5039	0.4769 – 0.5322	12
Avg return · LONG (bps)	-72.8	-137.4 – -55.3	12
Avg return · SHORT (bps)	-6.3865	-52.7 – 9.6361	12
Selection rate · LONG	0.0399	0.0357 – 0.0424	12
Selection rate · SHORT	0.0816	0.0697 – 0.0876	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

-103.3

short

-55.2

total

-158.6

appearances 284160 · LONG 11110 · SHORT 22264

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