International Journal of Innovative Research in Computer and Communication Engineering

ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines

| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |


TITLE Alcohol Quality Prediction
ABSTRACT Wine quality estimation from physicochemical measurements is a useful machine-learning benchmark, but a prediction interface must communicate uncertainty and avoid presenting a sensory score as a health or safety judgment. This paper describes an evaluated machine-learning dashboard for estimating wine quality from laboratory-style measurements. The work uses the UCI Wine Quality data, which contains red and white Vinho Verde wine records, and compares a set of regression approaches before selecting a Random Forest model for the deployed application. On a held-out test set of 1,300 records, the selected model achieved a root mean squared error (RMSE) of 0.600, mean absolute error (MAE) of 0.432, and coefficient of determination (R²) of 0.528; 66% of predictions were within 0.5 quality points of the recorded score. The system is implemented in Python with Streamlit and supports single-record prediction, batch CSV scoring, feature-importance visualisation, prediction history, and PDF reporting. Explanations are presented as model-based indicators rather than causal conclusions. The results suggest that physicochemical attributes contain useful but incomplete information about sensory quality. The system is a decision-support prototype and does not assess alcohol purity, toxicity, drinkability, or regulatory compliance.
AUTHOR ER. SANJEEV JIGALI, ADARSH PRAKASH AMBORE, CHANDRU FAKKIRAPPA LAMANI, RAGHAVENDRA SHRINIVAS MEHARWADE, AKASH VISHNURADDI YERESHEEMI Assistant Professor, Department of Computer Science and Engineering, STJIT, Ranebennur, India B.E. Students, Department of Computer Science and Engineering, STJIT, Ranebennur, India
VOLUME 189
DOI DOI: 10.15680/IJIRCCE.2026.1410019
PDF pdf/19_Alcohol Quality Prediction.pdf
KEYWORDS
References [1] P. Cortez, A. Cerdeira, F. Almeida, T. Matos, and J. Reis, “Modeling wine preferences by data mining from physicochemical properties,” Decision Support Systems, vol. 47, no. 4, pp. 547–553, 2009, doi: 10.1016/j.dss.2009.05.016.
[2]P . Cortez, “Wine Quality,” UCI Machine Learning Repository, 2009, doi: 10.24432/C56S3T. [Online]. Available: https://archive.ics.uci.edu/dataset/186/wine+quality
[3] “Enhancing red wine quality prediction through Machine Learning approaches with Hyperparameters optimization technique,” in Proc. 2nd Int. Conf. Electrical, Electronics, Information and Communication Technologies (ICEEICT), 2023, doi: 10.1109/ICEEICT56924.2023.10157719. [Author and page details to be verified on IEEE Xplore before submission.]
[4] F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
[5] Streamlit, “Streamlit documentation.” [Online]. Available: https://docs.streamlit.io/ (accessed Oct. 22, 2026).


Copyright © IJIRCCE 2020.All right reserved