per-stock model-accuracy decomposition

5026.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	0.3024	0.2728 – 0.3367	12
Hit rate · SHORT	0.6563	0.5836 – 0.7657	12
Avg return · LONG (bps)	-136.6	-156.3 – -101.5	12
Avg return · SHORT (bps)	174.0	62.3 – 266.5	12
Selection rate · LONG	0.0199	0.0180 – 0.0229	12
Selection rate · SHORT	0.0142	0.0121 – 0.0154	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

-133.6

short

116.8

total

-16.8

appearances 507840 · LONG 10326 · SHORT 7276

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