per-stock model-accuracy decomposition

2687.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	0.5938	0.3544 – 0.6169	12
Hit rate · SHORT	0.6807	0.5610 – 0.7697	12
Avg return · LONG (bps)	108.3	-18.3 – 202.1	12
Avg return · SHORT (bps)	141.3	-105.2 – 229.7	12
Selection rate · LONG	0.0095	0.0075 – 0.0105	12
Selection rate · SHORT	0.0097	0.0077 – 0.0212	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

15.5

short

-3.4973

total

12.0

appearances 113664 · LONG 1043 · SHORT 1627

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