per-stock model-accuracy decomposition

1783.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	0.4098	0.3799 – 0.5406	12
Hit rate · SHORT	0.5267	0.4950 – 0.5913	12
Avg return · LONG (bps)	-32.9	-58.5 – 49.2	12
Avg return · SHORT (bps)	29.1	-6.8447 – 122.3	12
Selection rate · LONG	0.0118	0.0106 – 0.0132	12
Selection rate · SHORT	0.0076	0.0061 – 0.0095	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

-15.0

short

27.9

total

12.9

appearances 538368 · LONG 6605 · SHORT 3960

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