per-stock model-accuracy decomposition

2195.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	0.3640	0.3216 – 0.4191	12
Hit rate · SHORT	0.7088	0.6872 – 0.7363	12
Avg return · LONG (bps)	-55.8	-162.4 – 8.8530	12
Avg return · SHORT (bps)	334.7	314.3 – 364.8	12
Selection rate · LONG	0.0255	0.0226 – 0.0276	12
Selection rate · SHORT	0.0318	0.0280 – 0.0369	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

-71.2

short

401.6

total

330.4

appearances 352512 · LONG 8713 · SHORT 11600

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