per-stock model-accuracy decomposition

3321.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	0.5502	0.4698 – 0.6486	12
Hit rate · SHORT	0.7778	0.7222 – 0.8333	2
Avg return · LONG (bps)	7.4698	-3.2042 – 31.5	12
Avg return · SHORT (bps)	-99.4	-133.9 – -64.9	2
Selection rate · LONG	0.0008	0.0006 – 0.0009	12
Selection rate · SHORT	0	0 – 0	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

0.3021

short

-0.0779

total

0.2242

appearances 721920 · LONG 525 · SHORT 12

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