Overview

Wine quality assessment is an important task in the food and beverage industry, helping producers maintain consistent product standards and assisting consumers in making informed choices. Traditionally, wine quality is evaluated by human experts through sensory analysis, but machine learning provides an efficient way to predict quality based on measurable physicochemical properties.

In this challenge, your task is to build a machine learning model that predicts the quality score of a wine sample using its physicochemical characteristics. You will work with a labeled tabular dataset containing chemical measurements of red and white wines, each paired with an expert-rated quality score ranging from 0 to 10. This challenge is beginner-friendly and offers hands-on experience with the complete machine learning workflow, including data preprocessing, exploratory data analysis, feature engineering, model training, and evaluation for multi-class classification problems.

Practice Skills

In this challenge, you will gain hands-on experience with:

• Python
• Data Preprocessing
• Exploratory Data Analysis (EDA)
• Feature Engineering
• Machine Learning Classification
• Model Evaluation

Evaluation

Goal

Train a classification model that predicts the quality score (0–10) for each wine sample in the test set based on its physicochemical properties.

Metric

Submissions are evaluated on Accuracy:

$\text{Accuracy} = \frac{\text{Correct Predictions}}{\text{Total Predictions}}$

Submission

Format

A CSV with two columns:

• id: The unique identifier for each wine sample.
• label: The predicted wine quality score (0–10).

id	quality
1001	4
1002	9
1002	7

See the submission guide for upload instructions.

Tracks

The challenge accepts two submission tracks:

• Public: predict on the public test set and upload the resulting CSV.
• Private: upload your model. It is scored on a held-out private test set. Your code must recursively scan the entire data directory.