per-stock model-accuracy decomposition

6537.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	0.3964	0.3220 – 0.4350	12
Hit rate · SHORT	0.5470	0.5358 – 0.5769	12
Avg return · LONG (bps)	-259.1	-272.8 – -232.5	12
Avg return · SHORT (bps)	354.6	329.9 – 408.9	12
Selection rate · LONG	0.0098	0.0089 – 0.0105	12
Selection rate · SHORT	0.0323	0.0307 – 0.0380	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

-69.3

short

331.1

total

261.8

appearances 274176 · LONG 2632 · SHORT 9333

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