per-stock model-accuracy decomposition

3409.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	0.3928	0.3703 – 0.4636	12
Hit rate · SHORT	0.4093	0.3849 – 0.4539	12
Avg return · LONG (bps)	-18.4	-41.3 – -4.2877	12
Avg return · SHORT (bps)	-15.8	-142.3 – 16.6	12
Selection rate · LONG	0.0369	0.0300 – 0.0394	12
Selection rate · SHORT	0.0169	0.0139 – 0.0188	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

-14.3

short

-19.1

total

-33.5

appearances 172032 · LONG 5962 · SHORT 2786

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