Wine quality assessment is traditionally based on expert sensory evaluation, which is subjective, time-consuming, and costly. The goal of this project is to predict wine quality using measurable physicochemical properties, enabling data-driven quality control and decision-making.
To develop a machine learning model that accurately predicts wine quality ratings based on chemical attributes such as acidity, alcohol content, sulphates, and pH.
The dataset contains physicochemical properties of wine samples including:
- Fixed acidity
- Volatile acidity
- Citric acid
- Residual sugar
- Chlorides
- Free & total sulfur dioxide
- Density
- pH
- Sulphates
- Alcohol
Target variable: Wine Quality Score
- R Programming
- Random Forest Algorithm
- Caret
- openxlsx
- tcltk (GUI-based prediction system)
- Data cleaning and preprocessing
- Exploratory data analysis
- Feature selection and model training
- Random Forest model implementation
- Model evaluation and validation
- GUI development for real-time prediction
- Algorithm: Random Forest
- Handles non-linear relationships and feature interactions effectively