Data Science SB / Jan 2024 – Feb 2024

Wine Quality Classifier

Compared five classifiers for red and white wine quality, reaching 84% accuracy from 11 physicochemical features and placing top five at the UCSB Datathon.

resume
timelineJan 2024 - Feb 2024
focusml
stack
  • Scikit-learn
  • Pandas
  • Jupyter Notebook

problem

Predict categorical wine quality reliably from 11 measured physicochemical properties.

approach

Prepared the data in Pandas, trained Random Forest, Ridge, SVM, MLP, and XGBoost classifiers, and compared their validation performance.

implementation notes

  • Compared Random Forest, Ridge Classifier, SVM, MLP, and XGBoost models for red and white wine quality classification.
  • Reached 84% accuracy from 11 physicochemical wine properties, placing in the top five at the UCSB Datathon.

impact

  • Best accuracy 84%
  • Placed top 5 in UCSB Datathon
accuracy
84%

recognition

  • Top 5 in UCSB Datathon