per-stock model-accuracy decomposition

3996.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	0.6105	0.5211 – 0.6613	12
Hit rate · SHORT	0.9048	0.7871 – 0.9514	12
Avg return · LONG (bps)	-83.4	-139.9 – 41.5	12
Avg return · SHORT (bps)	432.9	275.2 – 477.0	12
Selection rate · LONG	0.0026	0.0023 – 0.0036	12
Selection rate · SHORT	0.0016	0.0008 – 0.0022	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

-10.7

short

26.5

total

15.8

appearances 477696 · LONG 1428 · SHORT 795

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