Machine Learning-Based Wine Quality Predictive Modelling

Xiang Li

2024

Abstract

With the continuous economic development and the trend of consumption upgrading, there is a growing demand for high-quality wines in the market. Currently, the evaluation of wine quality primarily relies on scores provided by professional wine tasters. However, leveraging wine physicochemical indicators for efficient and accurate quality assessment has become increasingly crucial in the industry. In this study, we utilized a wine dataset sourced from Kaggle to develop and train four machine learning models for predicting wine quality. To address the issue of imbalanced classes, we incorporated oversampling techniques during the model training process. Our results demonstrated a significant enhancement in the performance of the models, with the Random Forest model emerging as the optimal choice. It achieved an accuracy rate of 90.71% for red wine dataset and an impressive accuracy rate of 93.79% for white wine dataset. The findings of this research underscore the importance of integrating machine learning techniques with wine physicochemical indicators to enhance the accuracy and efficiency of wine quality assessment.

Paper Citation

in Harvard Style

Li X. (2024). Machine Learning-Based Wine Quality Predictive Modelling. In Proceedings of the 1st International Conference on Innovations in Applied Mathematics, Physics and Astronomy - Volume 1: IAMPA; ISBN 978-989-758-722-1, SciTePress, pages 86-92. DOI: 10.5220/0012998000004601

in Bibtex Style

@conference{iampa24,
author={Xiang Li},
title={Machine Learning-Based Wine Quality Predictive Modelling},
booktitle={Proceedings of the 1st International Conference on Innovations in Applied Mathematics, Physics and Astronomy - Volume 1: IAMPA},
year={2024},
pages={86-92},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012998000004601},
isbn={978-989-758-722-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Innovations in Applied Mathematics, Physics and Astronomy - Volume 1: IAMPA
TI - Machine Learning-Based Wine Quality Predictive Modelling
SN - 978-989-758-722-1
AU - Li X.
PY - 2024
SP - 86
EP - 92
DO - 10.5220/0012998000004601
PB - SciTePress