per-stock model-accuracy decomposition

2820.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	0.5425	0.4385 – 0.5764	12
Hit rate · SHORT	0.9701	0.9491 – 0.9945	12
Avg return · LONG (bps)	8.5972	-29.8 – 57.0	12
Avg return · SHORT (bps)	197.8	178.5 – 251.1	12
Selection rate · LONG	0.0032	0.0025 – 0.0051	12
Selection rate · SHORT	0.0034	0.0025 – 0.0041	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

1.8438

short

33.1

total

34.9

appearances 501504 · LONG 1834 · SHORT 1714

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