Indonesian Coffee Recommendation System Based on Aroma and Flavor Profiles Using the K-Means Clustering Algorithm

Muhammad Fachmi Syahrial, Arif Nur Rohman, Ika Nur Fajri

Abstract


The diversity of Indonesian coffee sensory profiles presents both potential and a practical challenge: consumers struggle to find coffee that matches their taste preferences due to the absence of a system that recommends options based on measurable sensory attributes. This study develops a Nusantara coffee recommendation system using K-Means Clustering with 50 Indonesian coffee sensory records collected automatically via web scraping from Coffee Review, a professional coffee rating platform, covering five quantitative attributes: Aroma, Acidity, Body, Flavor, and Aftertaste. Following Min-Max normalization, the K-Means algorithm with k-means++ initialization produced three optimal clusters (K=3), determined through a combination of the Elbow Method, Silhouette Score (0.4889), Davies-Bouldin Index (0.831), and Calinski-Harabasz Score (45.41). The system recommends the top-3 coffees based on Euclidean distance between user preference input and the nearest cluster centroid. Black Box Testing across five scenarios confirmed all functions performed as expected (5/5). This study contributes a sensory-profile-based approach that eliminates the cold-start problem in coffee recommendation systems, with potential integration into local coffee applications and Indonesian coffee e-commerce platforms.

Keywords


Acidity;Aroma;K-Means Clustering;Nusantara Coffee;Recommendation System;Web Scraping

Full Text:

PDF

References


K. P. Sinaga and M. S. Yang, “Unsupervised K-means Clustering Algorithm,” IEEE Access, Vol. 8, pp. 80716–80727, 2020, DOI: 10.1109/ACCESS.2020.2988796.

M. Muzaifa and et al., “Physicochemical and Sensory Characteristics of Three Types of Wine Coffees from Bener Meriah Regency, Aceh Indonesia,” IOP Conf. Ser. Earth Environ. SCI., Vol. 1183, p. 12061, 2023, DOI: 10.1088/1755-1315/1183/1/012061.

W. David, M. Intania, P. Purnama, and I. Iswaldi, “Characteristics of Commercial Single-Origin Organic Coffee in Indonesia,” Food SCI. Technol., Vol. 43, p. e118522, 2023, DOI: 10.1590/fst.118522.

H. Purwawangsa, M. I. Irfany, and D. A. Haq, “Indonesian Coffee Exports Competitiveness and Determinants,” J. Manaj. dan Agribisnis, Vol. 21, No. 1, pp. 59–71, 2024, DOI: 10.17358/jma.21.1.59.

J. Huang, Z. Jia, and Z. Peng, “Improved Collaborative Filtering Personalized Recommendation Algorithm based on K-Means Clustering and Weighted Similarity on the Reduced Item Space,” Math. Model. Control, Vol. 3, No. 1, pp. 39–49, 2023, DOI: 10.3934/mmc.2023004.

I. M. E. Kundiman and et al., “Product and Store Recommendation System using K-Means Clustering and Hybrid Filtering on Marketplace,” J. La Multiapp, Vol. 6, No. 4, pp. 837–848, 2025, DOI: 10.37899/journallamultiapp.v6i4.2378.

K. Tabianan, S. Velu, and V. Ravi, “K-Means Clustering Approach for Intelligent Customer Segmentation using Customer Purchase Behavior Data,” Sustainability, Vol. 14, No. 12, p. 7243, 2022, DOI: 10.3390/su14127243.

A. M. Ikotun, A. S. Ezugwu, L. Abualigah, B. Abuhaija, and J. Heming, “K-Means Clustering Algorithms: A Comprehensive review, Variants Analysis, and Advances in the Era of Big Data,” Inf. SCI. (Ny)., Vol. 622, pp. 178–210, 2023, DOI: 10.1016/j.ins.2022.11.139.

D. Kowald, D. Yang, and E. Lacic, “Editorial: Reviews in Recommender Systems: 2022,” Front. Big Data, Vol. 7, p. 1384460, 2024, DOI: 10.3389/fdata.2024.1384460.

C. Review, “Indonesian Coffee Reviews,” Jun. 2024. [Online]. Available: https://www.coffeereview.com/types/indonesian/

K. R. Shahapure and C. Nicholas, “Cluster Quality Analysis using Silhouette Score,” 2020. DOI: 10.1109/DSAA49011.2020.00096.

M. Shutaywi and N. N. Kachouie, “Silhouette Analysis for Performance Evaluation in Machine Learning with Applications to Clustering,” Entropy, Vol. 23, No. 6, p. 759, 2021, DOI: 10.3390/e23060759.

M. Faisal, E. M. Zamzami, and Sutarman, “Comparative Analysis of Inter-Centroid K-Means Performance using Euclidean Distance, Canberra Distance and Manhattan Distance,” J. Phys. Conf. Ser., Vol. 1566, No. 1, p. 12112, 2020, DOI: 10.1088/1742-6596/1566/1/012112.

Y. Abubakar, D. Hasni, H. P. Widayat, M. Muzaifa, and Mahdi, “Effect of Varieties and Processing Practices on the Physical and Sensory Characteristics of Gayo Arabica Specialty Coffee,” IOP Conf. Ser. Mater. SCI. Eng., Vol. 523, No. 1, p. 12027, 2019, DOI: 10.1088/1757-899X/523/1/012027.

Y. Abubakar and et al., “Sensory Characteristic of Espresso Coffee Prepared from Gayo Arabica Coffee Roasted at Various Times and Temperatures,” IOP Conf. Ser. Earth Environ. SCI., Vol. 667, p. 12048, 2021, DOI: 10.1088/1755-1315/667/1/012048.

J. N. Bondevik, K. E. Bennin, Ö. Babur, and C. Ersch, “A Systematic Review on Food Recommender Systems,” Expert Syst. Appl., Vol. 238, p. 122166, 2024, DOI: 10.1016/j.eswa.2023.122166.

A. A. Patoulia, A. Kiourtis, A. Mavrogiorgou, and D. Kyriazis, “A Comparative Study of Collaborative Filtering in Product Recommendation,” Emerg. SCI. J., Vol. 7, No. 1, pp. 1–15, 2023, DOI: 10.28991/ESJ-2023-07-01-01.

R. Yera, A. A. Alzahrani, L. Martínez, and R. M. Rodríguez, “A Systematic Review on Food Recommender Systems for Diabetic Patients,” Int. J. Environ. Res. Public Health, Vol. 20, No. 5, p. 4248, 2023, DOI: 10.3390/ijerph20054248.

P. J. Muhammad Ali, “Investigating the Impact of Min-Max Data Normalization on the Regression Performance of K-Nearest Neighbor with Different Similarity Measurements,” ARO - Sci. J. Koya Univ., Vol. 10, No. 1, pp. 85–91, 2022, DOI: 10.14500/aro.10955.

M. Rostami, V. Farrahi, S. Ahmadian, S. M. J. Jalali, and M. Oussalah, “A Novel Healthy and Time-Aware Food Recommender System using Attributed Community Detection,” Expert Syst. Appl., Vol. 221, p. 119719, 2023, DOI: 10.1016/j.eswa.2023.119719.




DOI: https://doi.org/10.32520/stmsi.v15i7.6379

Article Metrics

Abstract view : 6 times
PDF - 0 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.