qbuntuqbuntu

カーリット (4275.T) quant model fit

4275.T·素材・化学·jp-listed
computed asof 2026-10-01T02:33:09

Median hit rate and return when a model selected カーリット (4275.T). Model: ml-factor-lgbm-9f-jp-growth. Model–stock fit, not a buy signal.

Median LONG hit rate is 0.17 (n=12). below a coin flip.Median LONG return is +3.5 bps.

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 — strategy verdict: marginal. 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)

metricmedianp25 – p75n
Hit rate · LONG0.17420.0357 – 0.632812
Hit rate · SHORT0.11110.0541 – 0.20009
Avg return · LONG (bps)3.5411-71.7 – 40.412
Avg return · SHORT (bps)-177.0-203.5 – -87.69
Selection rate · LONG0.00020.0001 – 0.000312
Selection rate · SHORT0.00010 – 0.000312

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%). Metrics with n = 0 are omitted.

PnL contribution

long
-0.2767
short
-2.2030
total
-2.4797

Selected LONG 156 / SHORT 129 times out of 840,960 appearances (0.019% LONG).

sum of per-trade decimal returns across all grid combos and retrain periods (0.01 = one trade returning 1%)

/ai/stocks/4275.T.md/v1/stocks/4275.T
Research, not investment advice. Metrics describe model–stock fit, not the stock's merit.