Optimized LightGBM Model for Predicting Total Cup Points of Arabica Coffee using Sensory Cupping Data
DOI:
https://doi.org/10.26905/jtmi.v11i2.16348Keywords:
Arabica coffee, sensory cupping, LightGBM, Coffee quality prediction, machine learningAbstract
Evaluating coffee quality through sensory cupping is essential but inherently subjective, as scoring depends on the consistency and expertise of professional panelists. To improve objectivity, this study applies the Light Gradient Boosting Machine (LightGBM) algorithm to predict the Total Cup Points of Arabica coffee using sensory evaluation data. The dataset, obtained from the Coffee Quality Institute Arabica Reviews (May 2023), contains 1,509 cupping records assessed according to the Specialty Coffee Association (SCA) protocol. Nine sensory attributes aroma, flavor, aftertaste, acidity, body, balance, uniformity, clean cup, and sweetness were used as predictors. The modeling process included data preprocessing, feature selection, hyperparameter tuning using RandomizedSearchCV, and performance evaluation through 5-Fold and 10 Fold Cross-Validation. The tuned LightGBM model achieved an R² of 0.9634 and an RMSE of 0.4673 under the 10-Fold scheme. Comparative analysis showed that LightGBM produced lower prediction error than XGBoost, Random Forest, and Support Vector Regression (SVR) when evaluated under identical default parameter settings. Feature importance indicated that flavor, balance, clean cup, and aftertaste were the most influential contributors to total cup points. The findings provide a reliable computational framework to support more objective, consistent, and efficient coffee cupping assessments
Downloads
References
[1] Badan Pusat Statistik, “Ekspor Kopi Menurut Negara Tujuan Utama Tahun 2000-2024,” Badan Pusat Statistik. [Online]. Available: Https://Www.Bps.Go.Id/Id/Statistics-Table/1/Mtaxncmx/Ekspor-Kopi-Menurut-Negara-Tujuan-Utama--2000-2024
[2] A. Ghoshray And E. Mise, “Whither The Price Of Coffee? An Analysis Of Trends And Shocks Since The Coffee Crisis,” Empir. Econ., Vol. 68, No. 6, Pp. 2655–2672, 2025, Doi: 10.1007/S00181-025-02716-1.
[3] M. Al-Mahish And R. Alfayadh, “The Impact Of Coffee Quality Attributes And Ratings On Specialty Coffee Bean Prices,” Beverage Plant Res., Vol. 4, No. 1, Pp. 0–0, 2024, Doi: 10.48130/Bpr-0024-0029.
[4] K. Muiz, N. Nilahayati, N. Nasruddin, J. Jamidi, And H. Hafifah, “Analisis Kualitas Fisik Dan Cita Rasa Kopi Arabika (Coffea Arabica L.) Pada Dua Rentang Ketinggian,” J. Agrium, Vol. 21, No. 3, P. 258, 2024, Doi: 10.29103/Agrium.V21i3.18994.
[5] M. F. Kurniawan, D. Qisthina, And T. Fitrilia, “Karakteristik Sensori Dan Fisikokimia Seduhan Kopi Sangrai Liberika, Arabika, Dan Robusta Dari Indonesia,” Food Sci. J. Food Sci. Technol., Vol. 4, No. 2, Pp. 100–113, 2024, Doi: 10.33830/Fsj.V4i2.9063.2024.
[6] D. Qisthina, Muhammad Fakih Kurniawan, And Tiana Fitrilia, “Deskripsi Atribut Sensori Tiga Jenis Kopi (Arabika, Robusta, Dan Liberika) Asal Indonesia Dan Hasil Cupping Score,” Karimah Tauhid, Vol. 3, No. 8, Pp. 9031–9042, 2024, Doi: 10.30997/Karimahtauhid.V3i8.14611.
[7] Specialty Coffee Association, “Cupping Protocol,” 2020. [Online]. Available: Https://Sca.Coffee/Research/Protocols-Best-Practices
[8] F. Adam, R. Agustina, And R. Fadhil, “Pengujian Cita Rasa Kopi Arabika Dengan Metode Cupping Test,” J. Ilm. Mhs. Pertan., Vol. 7, No. 1, Pp. 517–521, Mar. 2022, Doi: 10.17969/Jimfp.V7i1.19021.
[9] D. Hamdhana, M. Yusra, N. A. Yunita, R. G. Putri, A. Arliansyah, And M. Mardiaton, “Pembekalan Keterampilan Cupping Kopi Pada Generasi Milenial Di Aceh Utara,” J. Pengabdi. Sos., Vol. 2, No. 2, Pp. 2708–2716, 2024, Doi: 10.59837/Aaamvz25.
[10] D. Giacalone, I. Steen, J. Alstrup, And M. Münchow, “Inter-Rater Reliability Of ‘Clean Cup’ Scores By Coffee Experts,” J. Sens. Stud., Vol. 35, No. 5, 2020, Doi: 10.1111/Joss.12596.
[11] F. Amalia Et Al., “Identification Of Potential Quality Markers In Indonesia’s Arabica Specialty Coffee Using GC/MS-Based Metabolomics Approach,” Metabolomics, Vol. 19, No. 11, Pp. 1–11, 2023, Doi: 10.1007/S11306-023-02051-5.
[12] Z. Iqbal Et Al., “Studi Miniatur Uv/Vis/Nir Spektrometer Untuk Proses Kuantifikasi Mutu Biji Kopi Dengan Protokol Cupping Test,” J. Teknotan, Vol. 18, No. 1, P. 1, 2024, Doi: 10.24198/Jt.Vol18n1.1.
[13] A. Michael And J. Rusman, “Jurnal Teknologi Dan Manajemen Informatika Klasifikasi Cacat Biji Kopi Menggunakan Metode Transfer Learning Dengan Hyperparameter Tuning Gridsearch,” Vol. 9, No. 1, Pp. 37–45, 2023.
[14] H. Basri, H. Darwis, And F. Umar, “Jurnal Teknologi Dan Manajemen Informatika Klasifikasi Daun Herbal Menggunakan K-Nearest Neighbor Dan Convolutional Neural Network Dengan Ekstraksi Fourier Descriptor,” Vol. 9, No. 2, Pp. 79–90, 2023.
[15] R. P. Putra And F. Marisa, “Jurnal Teknologi Dan Manajemen Informatika Klasifikasi Jenis Kanker Prostat Melalui Citra MRI Menggunakan Pengolahan Citra Digital,” Vol. 10, No. 2, Pp. 143–153, 2024.
[16] X. Sun, “Application Of An Improved Lightgbm Hybrid Integration Model Combining Gradient Harmonization And Jacobian Regularization For Breast Cancer Diagnosis,” Sci. Rep., Vol. 15, No. 1, Pp. 1–18, 2025, Doi: 10.1038/S41598-025-86014-X.
[17] P. Septiana Rizky, R. Haiban Hirzi, And U. Hidayaturrohman, “Perbandingan Metode Lightgbm Dan Xgboost Dalam Menangani Data Dengan Kelas Tidak Seimbang,” J Stat. J. Ilm. Teor. Dan Apl. Stat., Vol. 15, No. 2, Pp. 228–236, 2022, Doi: 10.36456/Jstat.Vol15.No2.A5548.
[18] B. R. Prasetyo, E. D. Wahyuni, And P. M. Kusumantara, “Komparasi Performa Model Berbasis Algoritma Random Forest Dan Lightgbm Dalam Melakukan Klasifikasi Diabetes Melitus Gestasional,” J. Inform. Dan Tek. Elektro Terap., Vol. 12, No. 3, Pp. 481–490, 2024, Doi: 10.23960/Jitet.V12i3.4817.
[19] E. H. M. Tang, “Coffee Quality Institute - Arabica Reviews (May 2023),” 2023. [Online]. Available: Https://Www.Kaggle.Com/Datasets/Erwinhmtang/Coffee-Quality-Institute-Reviews-May2023
[20] Y. Cai, J. Feng, Y. Wang, Y. Ding, Y. Hu, And H. Fang, “The Optuna–Lightgbm–Xgboost Model: A Novel Approach For Estimating Carbon Emissions Based On The Electricity–Carbon Nexus,” Appl. Sci., Vol. 14, No. 11, 2024, Doi: 10.3390/App14114632.
[21] Microsoft, “Lightgbm Documentation,” 2024. [Online]. Available: Https://Lightgbm.Readthedocs.Io/
[22] P. Florek And A. Zagdański, “Benchmarking State-Of-The-Art Gradient Boosting Algorithms For Classification,” 2023, [Online]. Available: Http://Arxiv.Org/Abs/2305.17094
[23] I. K. Nti, O. Nyarko-Boateng, And J. Aning, “Performance Of Machine Learning Algorithms With Different K Values In K-Fold Crossvalidation,” Int. J. Inf. Technol. Comput. Sci., Vol. 13, No. 6, Pp. 61–71, 2021, Doi: 10.5815/Ijitcs.2021.06.05.
[24] M. F. Kurniawan Et Al., “Coffee Quality Prediction With Light Gradient Boosting Machine Algorithm Through Data Science Approach,” Appl. Sci., Vol. 4, No. 1, Pp. 563–573, Feb. 2024, Doi: 10.33395/Sinkron.V8i1.12169.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
(1)Â Copyright of the published articles will be transferred to the journal as the publisher of the manuscripts. Therefore, the author confirms that the copyright has been managed by the journal.
(2) Publisher of JTMI: Jurnal Teknologi dan Manajemen Informatika is University of Merdeka Malang.
(3) The copyright follows Creative Commons Attribution–ShareAlike License (CC BY SA): This license allows to Share — copy and redistribute the material in any medium or format, Adapt — remix, transform, and build upon the material, for any purpose, even commercially.
