per-stock model-accuracy decomposition

4918.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	0.5454	0.4779 – 0.6632	12
Hit rate · SHORT	0.6905	0.6276 – 0.7461	12
Avg return · LONG (bps)	35.4	-10.1 – 142.0	12
Avg return · SHORT (bps)	518.8	256.5 – 555.7	12
Selection rate · LONG	0.0161	0.0111 – 0.0211	12
Selection rate · SHORT	0.0118	0.0100 – 0.0156	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

15.7

short

73.5

total

89.3

appearances 139008 · LONG 2380 · SHORT 1661

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