per-stock model-accuracy decomposition

5612.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	0.4313	0.2793 – 0.4989	12
Hit rate · SHORT	0.8860	0.8393 – 0.9561	12
Avg return · LONG (bps)	24.1	-191.1 – 187.0	12
Avg return · SHORT (bps)	534.4	457.9 – 651.3	12
Selection rate · LONG	0.0041	0.0028 – 0.0046	12
Selection rate · SHORT	0.0132	0.0094 – 0.0161	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

-0.1859

short

167.9

total

167.8

appearances 238848 · LONG 968 · SHORT 3047

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