Perbandingan Algoritma K- Nearest Neighbor dan Naive Bayes Pada prediksi Harga saham Sektor Asuransi
DOI:
https://doi.org/10.30605/proximal.v9i1.7967Keywords:
K-Nearest Neighbor, Naïve Bayes, Prediksi, Harga Saham, AsuransiAbstract
Mengingat tingginya volatilitas pasar modal, kemampuan memprediksi pergerakan harga saham menjadi sangat krusial bagi investor dalam pengambilan keputusan strategis, khususnya pada sektor asuransi yang memiliki risiko yang dinamis. Penelitian ini bertujuan untuk membandingkan kinerja dua algoritma machine learning, yaitu K- Nearest Neighbor (KNN) dan Naïve Bayes dalam memprediksi harga saham di sektor asuransi. Penelitian ini mengimplementasikan kedua algortima tersebut untuk memprediksi naik atau turunnya harga saham. Metode yang digunakan adalah metode kuantitatif komparatif, di mana instrumen pengumpulan data dilakukan melalui studi dokumentasi data sekunder berupa riwayat harga saham harian. Penelitian mengolah data harian dari lima perusahaan asuransi, yaitu asuransi Ramayana, Jasa Tania, Sinarmas, Tugu dan Panin, selama periode Mei 2023 hingga april 2025. Teknik analisis data dilakukan melalui beberapa tahapan, meliputi data cleaning, pembagian data, proses penerapan algoritma, serta evaluasi model. Data dibagi menjadi 80% untuk data latih dan 20% untuk data uji. Hasil kinerja model dievaluasi menggunakan confusion matrix, meliputi akurasi, recall, dan presisi. KNN secara konsisten lebih unggul dan stabil hampir di semua perusahaan yang diteliti. Akurasi KNN secara konsisten berkisar antara 92,84% hingga 97,63%. Presisi KNN juga kuat, berkisar antara 81,94% hingga 98,21%. Recall KNN juga sangat tinggi, bahkan mencapai 100%. Naïve Bayes menunjukan kinerja yang kurang konsisten dan bervariasi. Akurasi Naïve Bayes jauh lebih rendah pada perusahan Ramayana (64,03%) dan Jasa Tania (67,64%). Presisi Naïve Bayes sangat rendah pada saham Ramayana (34,29%) dan Jasa Tania (56,69%). Recall Naïve Bayes juga bervariasi. Pada nilai recall Naïve Bayes menghasilkan nilai yang bervariasi dan turun pada Jasa Tania (27,34%) dan Ramayana (30,70%).
References
Argina, A. M. (2020). Penerapan Metode Klasifikasi K-Nearest Neigbor pada Dataset Penderita Penyakit Diabetes. Indonesian Journal of Data and Science, 1(2), 29–33. https://doi.org/10.33096/ijodas.v1i2.11
Gao, S. (2023). Trend-Based K-Nearest Neighbor Algorithm in Stock Price Prediction (Nomor Deca 2023). Atlantis Press International BV. https://doi.org/10.2991/978-94-6463-304-7_78
Hutapea, J. Y., Samuel, Y. T., & Sitorus, H. (2019). Comparison of Accuracy Between Two Methods: Naїve Bayes Algorithm and Decision Tree-J48 to Predict The Stock Price of Pt Astra International tbk Using Data From Indonesia Stock Exchange. Abstract Proceedings International Scholars Conference, 7(1), 1244–1258. https://doi.org/10.35974/isc.v7i1.1872
Kurnia, O. D., Fena, E. T. A., Yuliana, D., Ningrum, A., Daniati, E., & Ristyawan, A. (2024). Analisis Perbandingan Algoritma Naïve Bayes dengan K-Nearest Neighbor ( KNN ) Pada Dataset Mobile Price Classification. 8, 1174–1183.
Malkan, M., Kurniawan, I., & Noval, N. (2021). Pengaruh pengetahuan tentang pasar modal syariah terhadap minat investasi saham di pasar modal syariah. Jurnal Ilmu Perbankan dan Keuangan Syariah, 3(1), 57–73.
Nasution, M. R. A., & Hayaty, M. (2019). Perbandingan Akurasi dan Waktu Proses Algoritma K-NN dan SVM dalam Analisis Sentimen Twitter. Jurnal Informatika, 6(2), 226–235. https://doi.org/10.31311/ji.v6i2.5129
Niar, Y., Komariah, K., Surip, A., Saputra, R., & Ali, I. (2022). Implementasi Algoritma Naïve Bayes Untuk Prediksi Persediaan Barang Rotan. KOPERTIP : Jurnal Ilmiah Manajemen Informatika dan Komputer, 4(1), 28–34. https://doi.org/10.32485/kopertip.v4i1.112
Setiadi, D. (2024). Analisis Prediksi Harga Beras Berbasis Kualitas Menggunakan Algoritma K- Nearest Neighbord. 15(3), 106–115.
Sudriyanto, S., Syahro, F., & Fitriani, N. (2023). Perbandingan Performa Model Machine Learning Support Vector Machine, Neural Network, Dan K-Nearest Neighbors Dalam Prediksi Harga Saham. Jurnal Advanced Research Informatika, 2(1), 13–21. https://doi.org/10.24929/jars.v2i1.2983
Tauran, E. R. (2021). Prediksi Harga Saham Pt Bank Central Asia Tbk Berdasarkan Data Dari Bursa Efek Indonesia Menggunakan Metode K-Nearest Neighbors (Knn). TeIKa, 11(2), 123–129. https://doi.org/10.36342/teika.v11i2.2609
Triana, A. R., Putri, A. A., Mar’atussholikhah, K., Sukma, V. S., & Hidayat, M. F. (2024). Kepastian Hukum dalam Penanaman Modal Investasi di Kawasan Ekonomi Khusus dari Perspektif Investor. Jurnal Hukum, Politik dan Humaniora, 1(3), 246–262.
Virza, V. P., Tri Pranot, G., & Eko Putra, F. (2023). Klasifikasi Kebutuhan Sparepart Dengan Algoritma K-Nearest Neighbor Untuk Meningkatkan Penjualan Sparepart. Bulletin of Information Technology (BIT), 4(3), 287–293. https://doi.org/10.47065/bit.v4i3.729
Wang, Y., Xie, Y., Wu, Y., & Yang, Y. (2024). Improved KNN-based Stock Price Prediction. Academic Journal of Computing & Information Science, 7(6), 38–43. https://doi.org/10.25236/ajcis.2024.070606
Webb, G. I. (2020). Encyclopedia of Machine Learning and Data Science. Encyclopedia of Machine Learning and Data Science, April. https://doi.org/10.1007/978-1-4899-7502-7
Windy Mardiyyah, N., Rahaningsih, N., & Ali, I. (2024). Penerapan Data Mining Menggunakan Algoritma K-Nearest Neighbor Pada Prediksi Pemberian Kredit Di Sektor Finansial. JATI (Jurnal Mahasiswa Teknik Informatika), 8(2), 1491–1499. https://doi.org/10.36040/jati.v8i2.9010
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Rina Nurhayati, Pramesti Melyna Mushtofa, Fithri Sri Mulyani
This work is licensed under a Creative Commons Attribution 4.0 International License.
In submitting the manuscript to the journal, the authors certify that:
- They are authorized by their co-authors to enter into these arrangements.
- The work described has not been formally published before, except in the form of an abstract or as part of a published lecture, review, thesis, or overlay journal.
- That it is not under consideration for publication elsewhere,
- That its publication has been approved by all the author(s) and by the responsible authorities – tacitly or explicitly – of the institutes where the work has been carried out.
- They secure the right to reproduce any material that has already been published or copyrighted elsewhere.
- They agree to the following license and copyright agreement.
License and Copyright Agreement
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution License (CC BY 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
