per-stock model-accuracy decomposition

2156.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	0.2584	0.1664 – 0.3484	12
Hit rate · SHORT	0.1817	0.1718 – 0.2318	12
Avg return · LONG (bps)	-349.7	-472.5 – -174.7	12
Avg return · SHORT (bps)	-367.3	-519.0 – -271.9	12
Selection rate · LONG	0.0309	0.0249 – 0.0342	12
Selection rate · SHORT	0.0797	0.0757 – 0.0802	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

-64.2

short

-224.8

total

-289.0

appearances 69120 · LONG 2164 · SHORT 5388

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