High-Accuracy Wine Prediction Model Using Machine Learning

EasyChair Preprint 11354

Abstract

Both artificial intelligence and machine learning, emerging fields, seek to comprehend the structure of any supplied data and create models that properly fit and can effectively carry out the required activity. These days, machine learning is widely used in a variety of industries, including corporations, hospitals, and stock markets. Inspired by this, we created a high-accuracy wine prediction project using machine learning. To ensure that we obtain the best accurate result possible, we utilize numerous supervised machine learning models in this project, including logistic regression, random forest classifier, XGBoost, and SVC. This model demonstrates that the random forest classifier model, which has a training accuracy of 1.0(100 percent) and a validation accuracy of 0.831688596491228(84 percent), is the most accurate model. This model demonstrates how supervised machine learning can be used to forecast wine models. This will make it easier for wine producers to take charge of the quality of their output.

Keyphrases: Artificial Intelligence(AI), Supervised Machine Learning, wine quality prediction

@booklet{EasyChair:11354,
  author    = {Shreyas Nimbalkar and Sanjay Agrawal},
  title     = {High-Accuracy Wine Prediction Model Using Machine Learning},
  howpublished = {EasyChair Preprint 11354},
  year      = {EasyChair, 2023}}