THE RESULT
What the data shows
The largest computed metric is 0.6233 for Random forest; the smallest is 0.2019 for Prior baseline. Metric: average_precision (Average precision).
Seven is an analytical threshold, not a universal commercial standard. Quality itself is excluded from predictors.
| model | accuracy | balanced accuracy | macro f1 | roc auc | average precision | brier |
|---|---|---|---|---|---|---|
| Prior baseline | 0.7981 | 0.5 | 0.4439 | 0.5 | 0.2019 | 0.1612 |
| Logistic regression | 0.8168 | 0.6108 | 0.6309 | 0.7849 | 0.5158 | 0.1303 |
| Random forest | 0.8393 | 0.6666 | 0.6955 | 0.8542 | 0.6233 | 0.1141 |
THE METHOD
From source to answer
Binary target specified before analysis; grouped-input classification against prior prevalence.
The Python source exposes this study’s transformations. The complete project download includes shared preparation and evaluation routines.
EVALUATION
How the result was checked
Fixed 80/20 split of unique input groups (seed 42); exact input duplicates stay together.
Fixed models; default decision threshold; no holdout tuning.
Target and input features
Target: higher_rated
Inputs: fixed_acidity, volatile_acidity, citric_acid, residual_sugar, chlorides, free_sulfur_dioxide, total_sulfur_dioxide, density, ph, sulphates, alcohol, wine_type
THE NEXT DECISION
What follows from the finding
Evaluate a prospective screening workflow with external batches before using the ranking.
Where the conclusion stops
Sensory scores are ordinal and concentrated in the middle. Producer and batch IDs are unavailable. Associations are not recipes for changing quality or evidence of market price.
Related studies may reuse observations or holdouts. These are historical analyses; associations and backtests do not demonstrate commercial impact. Further model tuning needs new, untouched evaluation data.