per-stock model-accuracy decomposition

6840.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	0.2495	0.2026 – 0.3083	12
Hit rate · SHORT	0.1307	0.1037 – 0.2407	12
Avg return · LONG (bps)	-114.9	-129.4 – -90.4	12
Avg return · SHORT (bps)	48.1	-2.8613 – 117.0	12
Selection rate · LONG	0.0062	0.0056 – 0.0069	12
Selection rate · SHORT	0.0018	0.0014 – 0.0022	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

-31.4

short

6.4279

total

-24.9

appearances 412416 · LONG 2610 · SHORT 750

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