Research Article
Hybrid XGBoost and Neural Network Model for Accurate Wine Quality Prediction
@INPROCEEDINGS{10.4108/eai.28-4-2025.2357992, author={Chelluri Alekhya and Kesireddy Krupa Dhaneswari and Kottakota Mohan Babu and Ariveni Vijaya Venkata Padmasri and Tutta Lakshmi Subramanyam and Reethika Damarla}, title={Hybrid XGBoost and Neural Network Model for Accurate Wine Quality Prediction}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part II}, publisher={EAI}, proceedings_a={ICITSM PART II}, year={2025}, month={10}, keywords={wine quality prediction xgboost neural networks hybrid models}, doi={10.4108/eai.28-4-2025.2357992} }- Chelluri Alekhya
Kesireddy Krupa Dhaneswari
Kottakota Mohan Babu
Ariveni Vijaya Venkata Padmasri
Tutta Lakshmi Subramanyam
Reethika Damarla
Year: 2025
Hybrid XGBoost and Neural Network Model for Accurate Wine Quality Prediction
ICITSM PART II
EAI
DOI: 10.4108/eai.28-4-2025.2357992
Abstract
To summarize, in this study, a hybrid model of wine quality prediction that integrates the strengths of XGBoost and neural networks is introduced. The ability of XGBoost in feature selection and its capability of understanding complex non-linear correlations is combined with the learning power of neural networks, deep learning to capture complex patterns in data. The model is trained on a large dataset of wine physicochemical features, focusing on optimizing not only the prediction performance but also on generalization abilities. To evaluate the model efficiency, analysis measurement metrics such as the Mean Absolute Error , Root Mean Squared Error RMSE, and the R-squared are used. Based on experimental results, the hybrid model outperforms traditional machine learning models with higher accuracy and robust performance.
