per-stock model-accuracy decomposition

7822.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	0.3000	0.1667 – 0.6250	9
Hit rate · SHORT	0.0833	0.0061 – 0.7857	10
Avg return · LONG (bps)	-31.6	-107.7 – 113.5	9
Avg return · SHORT (bps)	-181.0	-267.3 – 604.1	10
Selection rate · LONG	0.0007	0.0001 – 0.0022	12
Selection rate · SHORT	0.0017	0.0007 – 0.0079	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

2.2374

short

-1.6064

total

0.6310

appearances 63744 · LONG 97 · SHORT 238

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