WINE QUALITY CLUSTERING USING DBSCAN ON ALCOHOL AND MALIC ACID CHARACTERISTICS

I Putu Sukadana Eka Putra; I Putu Alfin Teguh Wahyudi; I Putu Bramasta Priadinata; Ida Bagus Nyoman Surya Berata Keniten; I Putu Sugiartawan; I Gede Iwan Sudipa

Authors

I Putu Sukadana Eka Putra Institut Bisnis dan Teknologi Indonesia
I Putu Alfin Teguh Wahyudi Institut Bisnis dan Teknologi Indonesia
I Putu Bramasta Priadinata Institut Bisnis dan Teknologi Indonesia
Ida Bagus Nyoman Surya Berata Keniten Institut Bisnis dan Teknologi Indonesia
I Putu Sugiartawan Institut Bisnis dan Teknologi Indonesia
I Gede Iwan Sudipa Institut Bisnis dan Teknologi Indonesia

Keywords:

DBSCAN, Clustering, Wine Analysis, Alcohol, Malic Acid

Abstract

Wine is a premium product characterized by complex chemical properties, such as alcohol content, malic acid, and phenols, which influence sensory quality and serve as indicators for classification, quality assessment, and marketing. In the modern wine industry, chemical data analysis is critical for improving production efficiency and ensuring consistent quality. This study applies the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm to analyze wine data based on two key attributes: Alcohol and Malic Acid, which significantly influence flavor and acidity. The dataset comprises 178 wine samples normalized using the StandardScaler method for unbiased clustering. Through parameter optimization, the DBSCAN algorithm achieved optimal performance with eps = 0.5 and min_samples = 5. The analysis identified two main clusters and five outliers. The primary cluster (173 samples) exhibited an average alcohol content of 13.02% and malic acid level of 2.28, while outliers showed distinct characteristics, with an average alcohol content of 12.36% and malic acid level of 4.44. Clustering quality was validated using the Silhouette Score (0.42) and Davies-Bouldin Index (0.78), indicating satisfactory results. This research addresses the limited application of DBSCAN in wine quality analysis, highlighting its potential for identifying patterns and anomalies in chemical data. The study contributes to the wine industry by providing a data-driven framework for enhanced quality evaluation and classification, aligning with the growing demand for precise analytical methods to ensure product consistency and excellence.

References

Arfelli, G., Sartini, E., & Fabani, M. P. (2019). Wine Quality and Chemical Composition: Current Trends in Analytical Approaches. Food Chemistry, 2(1), 18–24.

Armaeni, P. P., Wiguna, I. K. A. G., & Parwita, W. G. S. (2024). Sentiment Analysis of YouTube Comments on the Closure of TikTok Shop Using Naïve Bayes and Decision Tree Method Comparison. Jurnal Galaksi, 1(2), 70–80. https://doi.org/10.70103/galaksi.v1i2.15

Belda, I., Zarraonaindia, I., Perisin, M., Palacios, A., & Acedo, A. (2022). From Vineyard Soil to Wine Fermentation: Microbiome Modulates the Flavour Profile of Wine. Frontiers in Microbiology, 13, 838–849.

Chen, J., Huang, K., & Zhang, W. (2020). Anomaly Detection in Industrial Sensor Data Using DBSCAN Clustering. Journal of Industrial Information Integration, 18, 100–120.

Ester, M., Kriegel, H. P., Sander, J., & Xu, X. (1996). A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise. Proceedings of KDD-96, 226–231.

Fadilah, N., & Wijayanto, H. (2023). Comparative Analysis of Clustering Methods on Chronic Kidney Disease Data. Journal of Data Science and Analytics, 5(2), 45–59.

Gutiérrez-Escobar, R., Aliaño-González, M. J., & Cantos-Villar, E. (2021). Wine Polyphenol Content and Its Influence on Wine Quality and Properties. Journal of the Science of Food and Agriculture, 101(1), 12–19.

Hastuti, N., Dewi, R. P., & Santoso, R. (2024). DBSCAN-Based Clustering for Optimizing Healthcare Worker Distribution in East Lombok. Indonesian Journal of Applied Sciences, 12(1), 78–85.

Jackson, R. S. (2021). Wine Science: Principles and Applications. Academic Press.

Lin, A. K. (2024). The AI Revolution in Financial Services: Emerging Methods for Fraud Detection and Prevention. Jurnal Galaksi, 1(1), 43–51. https://doi.org/10.70103/galaksi.v1i1.5

Murray, T., & Esteban, D. (2023). Clustering Environmental Data Using DBSCAN for Anomaly Detection. Environmental Data Journal, 7(3), 123–136.

Renault, P., Coulon, J., de Revel, G., & Bely, M. (2022). Wine Fermentation: Impact of Alcohol and Acidity on Flavor Development. Applied Microbiology and Biotechnology, 105(3), 14–25.

Rodríguez-Bencomo, J. J., Orriols, I., & Herrero, P. (2021). Evaluation of Acid Profiles in Wine Using Chemometric Analysis. Food Research International, 12(1), 101–108.

Saputro, J., Saini, K., & Valentine, H. M. (2024). Data Visualization of Higher Education Participation Rates in Indonesia Provinces. Jurnal Galaksi, 1(2), 101–109. https://doi.org/https://doi.org/10.70103/galaksi.v1i2.20

Suryadana, K., & Sarasvananda, I. B. G. (2024). Streamlining Inventory Forecasting with Weighted Moving Average Method at Parta Trading Companies. Jurnal Galaksi, 1(1), 12–21. https://doi.org/10.70103/galaksi.v1i1.2

Tarabella, A., & Burchi, B. (2021). Data Analysis in Wine Marketing: Trends and Perspectives. Wine Economics and Policy, 9(2), 56–63.

Zhang, Y., Li, X., & Liu, Z. (2021). An Application of DBSCAN in Financial Transaction Data Analysis. Journal of Financial Technology and Analytics, 9(1), 33–47.

Zhou, Y., & Wang, R. (2021). Clustering Techniques in Food Quality Evaluation. Food Analytical Methods, 14(5), 2341–2350.

Zhu, Y., Li, F., & Zhang, H. (2022). Application of Machine Learning in Wine Analysis: A Comprehensive Review. Trends in Food Science & Technology, 15(7), 123–135.