Penerapan Algoritma Decision Tree Untuk Klasifikasi Dan Prediksi Potabilitas Air Minum
Keywords:
Klasifikasi, Decision Tree, Machine Learning, Potabilitas Air, Kualitas AirAbstract
Ketersediaan air minum yang layak konsumsi (potabel) merupakan hal yang vital bagi kesehatan
masyarakat. Namun, data menunjukkan bahwa masih banyaknya sumber air yang terkontaminasi,
sehingga menimbulkan kebutuhan akan sistem deteksi yang akurat dan efisien. Penelitian ini bertujuan
untuk menerapkan algoritma Decision Tree dalam membangun model klasifikasi untuk memprediksi
potabilitas air minum berdasarkan serangkaian parameter fisika dan kimia. Dataset yang digunakan
bersumber dari Kaggle, terdiri dari 3.276 sampel data dengan 9 fitur atribut, yaitu: pH, Hardness, Solids,
Chloramines, Sulfate, Conductivity, Organic_carbon, Trihalomethanes, dan Turbidity, dengan variabel
target Potability (0 = Tidak Layak, 1 = Layak). Metodologi penelitian meliputi Exploratory Data Analysis
(EDA) untuk memahami karakteristik dari data, penanganan data hilang dengan teknik imputasi rata-rata
berdasarkan kelompok potabilitas, standardisasi data menggunakan StandardScaler, dan pembagian
dataset dengan rasio 80% untuk data latih dan 20% untuk data uji. Hasil evaluasi model menunjukkan
bahwa algoritma Decision Tree mampu mengklasifikasikan potabilitas air dengan akurasi sebesar 74.7%.
Analisis lebih lanjut menggunakan confusion matrix dan classification report mengungkapkan bahwa
model lebih baik dalam memprediksi kelas "Tidak Layak" (Precision: 0.79, Recall: 0.81) dibandingkan
kelas "Layak" (Precision: 0.66, Recall: 0.65), yang diidentifikasi sebagai dampak dari ketidakseimbangan
jumlah data pada kedua kelas. Kesimpulan dari penelitian ini adalah algoritma Decision Tree dapat
diimplementasikan sebagai alat yang efektif untuk memprediksi potabilitas air dengan kinerja yang baik
dan model yang mudah diinterpretasikan, meskipun perbaikan lebih lanjut diperlukan untuk menangani
data yang tidak seimbang.
Kata Kunci : Klasifikasi, Decision Tree, Machine Learning, Potabilitas Air, Kualitas Air.
ABSTRACT
The availability of potable drinking water is vital for public health. However, data indicates that many
water sources remain contaminated, creating a need for accurate and efficient detection systems. This
research aims to apply the Decision Tree algorithm to build a classification model for predicting drinking
water potability based on a series of physical and chemical parameters. The dataset used, sourced from
Kaggle, consists of 3,276 data samples with 9 feature attributes: pH, Hardness, Solids, Chloramines,
Sulfate, Conductivity, Organic_carbon, Trihalomethanes, and Turbidity, with the target variable Potability
(0 = Not Potable, 1 = Potable). The research methodology includes Exploratory Data Analysis (EDA) to
understand data characteristics, handling missing data using mean imputation based on potability groups,
data standardization using StandardScaler, and splitting the dataset with an 80% ratio for training data
and 20% for testing data. Model evaluation results show that the Decision Tree algorithm can classify
water potability with an accuracy of 74.7%. Further analysis using a confusion matrix and classification
report reveals that the model performs better at predicting the "Not Potable" class (Precision: 0.79, Recall:
0.81) compared to the "Potable" class (Precision: 0.66, Recall: 0.65), which is identified as an impact of
data imbalance between the two classes. The conclusion of this study is that the Decision Tree algorithm
can be implemented as an effective tool for predicting water potability with good performance and an easily
interpretable model, although further improvements are needed to address the imbalanced data.
References
[1] BPS (Badan Pusat Statistik), “Akses Terhadap Air Minum Layak Memang Menunjukkan Tren Peningkatan.,” Indonesia, 2023. Accessed: Oct. 17, 2025. [Online]. Available: https://www.bps.go.id/id/statistics-table/2/ODU0IzI=/persentase-rumah-tangga-yangmemiliki-akses-terhadap-sumber-air-minum-layak-menurut-provinsi-dan-klasifikasidesa--persen-.html
[2] Kementrian Kesehatan, “ Kemenkes Luncurkan Hasil Surveilans Kualitas Air Minum Rumah Tangga di Indonesia Tahun 2023,” https://kemkes.go.id/id/kemenkes-luncurkanhasil-surveilans-kualitas-air-minum-rumah-tangga-di-indonesia-tahun-2023, Jakarta, Dec. 20, 2024.
[3] Kemenkes RI., “Kemenkes: Lebih dari 40 Persen Air Minum Isi Ulang di RI Positif Mengandung E Coli Baca artikel detikHealth, ‘Kemenkes: Lebih dari 40 Persen Air Minum Isi Ulang di RI Positif Mengandung E Coli’ selengkapnya https://health.detik.com/berita-detikhealth/d-7695484/kemenkes-lebih-dari-40-persenair-minum-isi-ulang-di-ri-positif-mengandung-e-coli. Download Apps Detikcom Sekarang https://apps.detik.com/detik/,” Detik Health, Dec. 20, 2024.
[4] M. Sobron et al., IMPLEMENTASI ARTIFICIAL INTELLIGENCE PADA SYSTEM MANUFAKTUR TERPADU. 2021.
[5] S. Prasetyo and T. Dewayanto, “PENERAPAN MACHINE LEARNING, DEEP LEARNING, DAN DATA MINING DALAM DETEKSI KECURANGAN LAPORAN KEUANGAN-A SYSTEMATIC LITERATURE REVIEW,” DIPONEGORO JOURNAL
OF ACCOUNTING, vol. 13, no. 3, pp. 1–12, 2024, [Online]. Available: http://ejournals1.undip.ac.id/index.php/accounting
[6] L. Savitri and R. Nursalim, “Klasifikasi Kualitas Air Minum menggunakan Penerapan Algoritma Machine Learning dengan Pendekatan Supervised Learning,” Diophantine Journal of Mathematics and Its Applications, vol. 2, no. 01, pp. 30–36, Jun. 2023, doi: 10.33369/diophantine.v2i01.28260.
[7] S. Barad et al., “Comparative approach of decision tree and CWQI analysis for classification of groundwater with a special reference to fluoride ion in drought-prone Boudh district of Odisha, India,” Sustain Water Resour Manag, vol. 7, no. 6, p. 94, Dec. 2021, doi: 10.1007/s40899-021-00582-0.
[8] B.-G. Jo, W.-S. Jung, S.-H. Nam, and Y.-D. Kim, “Prediction of Cyanobacteria Using Decision Tree Algorithm and Sensor Monitoring Data,” Applied Sciences, vol. 13, no. 22,
p. 12266, Nov. 2023, doi: 10.3390/app132212266.
[9] W. Chen, D. Xu, B. Pan, Y. Zhao, and Y. Song, “Machine Learning-Based Water Quality Classification Assessment,” Water (Basel), vol. 16, no. 20, p. 2951, Oct. 2024, doi: 10.3390/w16202951.
[10] D. Danuri and M. Mohd Pozi, “Machine Learning Approaches for Fish Pond Water Quality Classification: Random Forest, Gaussian Naive Bayes, and Decision Tree Comparison,” in Proceedings of the 11th International Applied Business and Engineering Conference, ABEC 2023, September 21st, 2023, Bengkalis, Riau, Indonesia, EAI, 2024. doi: 10.4108/eai.21-9-2023.2342964.
[11] developerghost, “Water Potability,” https://www.kaggle.com/datasets/developerghost/water-potability.
[12] K. Abdi, A. Warjaya, I. Muthmainnah, and P. H. Pahutar, “Penerapan Algoritma Random Forest dalam Prediksi Kelayakan Air Minum,” Jurnal Ilmu Komputer dan Informatika, vol. 3, no. 2, pp. 81–88, Jan. 2024, doi: 10.54082/jiki.81.
[13] I. Ivanov and B. Toleva, “Predicting the Water Potability Index Using Machine Learning,” Environment and Ecology Research, vol. 11, no. 4, pp. 537–542, Aug. 2023, doi: 10.13189/eer.2023.110402.
[14] S. Dhummad, “The Imperative of Exploratory Data Analysis in Machine Learning,” Scholars Journal of Engineering and Technology, vol. 13, no. 01, pp. 30–44, Jan. 2025, doi: 10.36347/sjet.2025.v13i01.005.
[15] J. Peng, J. Hahn, and K.-W. Huang, “Handling Missing Values in Information Systems Research: A Review of Methods and Assumptions,” Information Systems Research, vol. 34, no. 1, pp. 5–26, Mar. 2023, doi: 10.1287/isre.2022.1104.
[16] Dewi, R., & Rizki, B. (2025). Pengaruh penggunaan fitur SpayLater dan flash sale Shopee terhadap perilaku konsumtif mahasiswa/i Muslim (Studi kasus pada mahasiswa/i FEB Universitas Potensi Utama). Jurnal Media Informatika, 6(3), 1634–1641. https://doi.org/10.55338/jumin.v6i3.5174
[17] Dermawan, D. A., & Pohan, Y. A. (2024). Pengaruh disiplin, pelatihan kerja dan pengembangan karir terhadap kinerja karyawan pada PT. Bank Sumut Cabang Imam Bonjol. Jurnal Dunia Pendidikan, 5(2), 450–465. https://doi.org/10.55081/jurdip.v5i2.3125
[18] Pohan, Y. A. (2024). Pengaruh kompensasi, lingkungan kerja non fisik dan stress kerja terhadap turnover intention karyawan pada PT. Mitra Tsunami Marine. Jurnal Widya, 5(2).
[19] Gianing, E., & Pohan, Y. A. (2024). Pengaruh kepemimpinan transformasional, lingkungan kerja, pengembangan karir terhadap kinerja pegawai di Rumah Sakit Sinar Husni Medan. Jurnal Widya, 5(2), 1972–1978. https://doi.org/10.54593/awl.v5i2.407
[20] Ramadhan, F., Wahyuni, E. S., & Prabowo, A. (2024). Perencanaan pensiun pada pekerja manufaktur di Kota Batam: Mengidentifikasi pengaruh sosial dan perilaku menabung. Jurnal Menara Ekonomi: Penelitian dan Kajian Ilmiah Bidang Ekonomi, 10(2), 65–78. https://doi.org/10.31869/me.v10i2.5935
[21] Pane, S. H., & Prabowo, A. (2024). The influence of service quality and physical evidence on student satisfaction Potensi Utama University. ePaper Bisnis: International Journal of Entrepreneurship and Management, 1(4), 01–16. https://doi.org/10.61132/epaperbisnis.v1i4.129
[22] Prabowo, A., Tanjung, Y., Wahyuni, E. S., & Aspan, H. (2025). Transformasi destinasi pemasaran: Model integratif pengembangan pariwisata berkelanjutan di kawasan objek wisata Sidebu-Debu, Kabupaten Karo Sumatera Utara. Economic and Education Journal (Ecoducation), 7(2), 455–476. https://doi.org/10.33503/ecoducation.v7i2.1687
[23] Lubis, K. S., Adam, A. A., Yusriadi, Y., Tanjung, A. P., & Azzahra, N. S. (2025). Analisis SWOT sebagai strategi penguatan daya saing UMKM depot air isi ulang pasca pendampingan manajerial dan digitalisasi. Jurnal Bisnis Kompetitif, 4(2), 154–159. https://doi.org/10.35446/bisniskompetif.v4i2.2368
[24] Gulo, M. K., & Tanjung, A. P. (2025). Analisis brand trust, sales promotion, shopping emotion, terhadap keputusan pembelian konsumen brand fashion UNIQLO. Jurnal Dunia Pendidikan, 5(4), 1289–1298. https://doi.org/10.55081/jurdip.v5i4.3552
[25] Kadariah, S., Syahrizal, R., & Sari, S. D. N. (2024). Eksistensi dan transformasi budaya lokal dalam strategi ketahanan ekonomi di Kota Padang Sumatera Barat. HUMAN FALAH: Jurnal Ekonomi dan Bisnis Islam, 11(2), 22–35. https://doi.org/10.30829/hf.v11i2.21763
[26] Nazli, P., & Kadariah, S. (2024). Implementasi akad al-qardh pada perbankan syariah (Studi kasus PT. Bank Sumut Cabang Syariah Medan). Jurnal Widya, 5(2), 2266–2276. https://doi.org/10.54593/awl.v5i2.436
[27] Aulanda, N. F., Hutagalung, M. A. K., Ridwan, M., & Aini, R. (2025). Effect of servant leadership on employee performance with work motivation as an intervening variable. Digital Business: Tren Bisnis Masa Depan, 16(1), 48–53. https://doi.org/10.59651/digital.v16i1.264
[28] Gemilang, F., & Hutagalung, M. A. K. (2025). Analysis of Murabahah financing risk management strategies at PT. BPRS Al-Washliyah Medan. BISEI: Jurnal Bisnis dan Ekonomi Islam, 10(2), 139–147. https://doi.org/10.33752/bisei.v10i2.10756
[29] Salsabilla, S., & Hutagalung, M. A. K. (2025). Analysis of the implementation of Islamic business ethics at Manna Supermarket Yogyakarta Campus. BISEI: Jurnal Bisnis dan Ekonomi Islam, 10(2), 108–116. https://doi.org/10.33752/bisei.v10i2.10757
[30] Eka Putra, S., Nurmala Sari, T., Simatupang, J., Murtani, A., & Tanjung, Y. (2025). Analysis of the benefits of the 7P marketing mix strategy on the brand image of Butong Tea at PT Perkebunan Nusantara IV Bah Butong. Jurnal Ilmiah Sosio-Ekonomika Bisnis, 28(2), 30–37. https://doi.org/10.22437/jiseb.v28i02.41506
Downloads
Published
License
Copyright (c) 2025 PROSIDING SEMINAR NASIONAL MULTI DISIPLIN ILMU (SENADIMU)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
