per-stock model-accuracy decomposition

2653.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	0.2128	0.1234 – 0.3500	11
Hit rate · SHORT	0	0 – 0	5
Avg return · LONG (bps)	-47.8	-63.0 – -25.8	11
Avg return · SHORT (bps)	-211.9	-211.9 – -211.9	5
Selection rate · LONG	0.0009	0.0005 – 0.0012	12
Selection rate · SHORT	0	0 – 0.0001	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

-1.4401

short

-0.2026

total

-1.6427

appearances 335616 · LONG 288 · SHORT 11

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