Comparative Analysis of K-Nearest Neighbors and Decision Tree Methods in Determining Students’ Purchase Interest  in MacBook Laptops

Intan   Fadilla Hasibuan; Deci   Irmayani; Volvo   Sihombing

doi:10.46729/ijstm.v5i5.1169

Intan Fadilla Hasibuan Faculty of Science and Technology, Universitas Labuhanbatu, Sumatera Utara Indonesia.
Deci Irmayani Faculty of Science and Technology, Universitas Labuhanbatu, Sumatera Utara Indonesia.
Volvo Sihombing Faculty of Science and Technology, Universitas Labuhanbatu, Sumatera Utara Indonesia.

DOI: https://doi.org/10.46729/ijstm.v5i5.1169

Keywords: Data Mining, Decision Tree, K-Nearest Neighbors, MacBook Laptop and Purchase Interest.

Abstract

In the context of increasingly competitive technology markets, companies need to know consumer preferences accurately to optimize product offerings and increase sales. Two classification methods that are often used in data mining, namely K-Nearest Neighbors and Decision Tree, have their own advantages and disadvantages. This study proposes a solution that involves processing student data using both classification methods to identify the most accurate and effective method for identifying purchase intentions. This study aims to compare the performance of the two methods in determining student purchase intentions for MacBook laptops. The research methodology includes collecting data from 100 students covering various factors such as user experience, design and portability, technical specifications, price, and security. This data is then classified using the K-Nearest Neighbors and Decision Tree methods. Furthermore, a confusion matrix is used to provide a more detailed picture of the performance of the two methods. The results of the study show that the Decision Tree method has a higher accuracy (91%) compared to K-Nearest Neighbors (88%). In addition, Decision Tree excels in other metrics such as precision (87.18% vs. 85.71%), recall (89.47% vs. 85.71%), specificity (91.94% vs. 89.66%), and F1-Score (88.31% vs. 85.71%). The decision tree also has a higher NPV value and lower FPR and FNR rates than K-Nearest Neighbors, indicating that it is superior in avoiding misclassification. The study's conclusion is that the Decision Tree method is more effective and accurate than K-Nearest Neighbors in determining students' purchase intentions for MacBook laptops. The decision tree shows better performance in almost all evaluation metrics, making it a more reliable method to use in consumer data analysis. The results of this study are expected to help companies choose a more appropriate and effective analysis method for their marketing strategies, as well as provide a basis for further research in the field of consumer purchase intention classification.

Downloads

Download data is not yet available.

References

[1] D. Arradian, “MacBook vs Windows: 10 Keunggulan MacBook yang Bikin Penggunanya Klepek-klepek!,” sindonews. [Online]. Available: https://tekno.sindonews.com/read/1345375/123/macbook-vs-windows-10-keunggulan-macbook-yang-bikin-penggunanya-klepek-klepek-1711080183
[2] W. Kurniasih, “Perbedaan Mac OS dan Windows OS,” gramedia.com. [Online]. Available: https://www.gramedia.com/best-seller/perbedaan-mac-os-dan-windows-os/
[3] J. Nasir, “Penerapan Data Mining Clustering Dalam Mengelompokan Buku Dengan Metode K-Means,” Simetris, vol. 11, no. 2, 2020, doi: 10.24176/simet.v11i2.5482.
[4] D. R. Y. TB, “Analisa Penerapan Data Mining pada Penerimaan Mahasiswa Politeknik Negeri Lhokseumawe Menggunakan Algoritma K-Means,” J. Informatics Comput. Sci., vol. 4, no. 2, pp. 208–216, 2018, [Online]. Available: http://jurnal.uui.ac.id/index.php/jics/article/view/749
[5] E. Mardiani et al., “Membandingkan Algoritma Data Mining dengan Tools Orange untuk Social Economy,” Digit. Transform. Technol., vol. 3, no. 2, pp. 686–693, 2023, doi: 10.47709/digitech.v3i2.3256.
[6] P. Kasandra, K. Vadilla, V. Audila, F. Zainal, and A. A. Dermawan, “Prediksi Nilai Emas Menggunakan Algoritma Regresi Linear,” IESM J., vol. 5, no. 1, pp. 152–165, 2024, doi: 10.22303/iesm.1.1.2021.01-10.
[7] K. Silvi Amalia, A. Purbaningrum, and R. Kusumastuti, “Analisis Pengelompokan Data Karyawan Terbaik Perusahaan Menggunakan Algoritma K-Means Clustering,” in Seminar Nasional Amikom Surakarta (SEMNASA), 2023, pp. 11–24.
[8] E. S. Rahmadina, B. Irawan, and A. Bahtiar, “Penerapan Algoritma Fuzzy C-Means pada Data Penjualan Distro,” JATI (Jurnal Mhs. Tek. Inform., vol. 8, no. 2, pp. 2348–2354, 2024, doi: 10.36040/jati.v8i2.8467.
[9] M. F. Haryanti et al., “Pengaruh Data Mining, Strategi Perusahaan Terhadap Laporan Kinerja Perusahaan,” J. Manaj. dan Bisnis, vol. 3, no. 1, pp. 71–90, 2024.
[10] P. Primadona and R. Fauzi, “Penerapan Data Mining Pada Penjualan Produk Elektronik,” Comput. Sci. Ind. Eng., vol. 9, no. 4, 2023, doi: 10.33884/comasiejournal.v9i4.7712.
[11] A. P. Permana, K. Ainiyah, and K. F. H. Holle, “Analisis Perbandingan Algoritma Decision Tree, kNN, dan Naive Bayes untuk Prediksi Kesuksesan Start-up,” JISKa (Jurnal Inform. Sunan Kalijaga), vol. 6, no. 3, pp. 178–188, 2021, doi: 10.14421/jiska.2021.6.3.178-188.
[12] D. J. Triani, M. H. Dar, and G. J. Yanris, “Analysis of Public Purchase Interest in Yamaha Motorcycles Using the K-Nearest Neighbor Method,” Sink. J. dan Penelit. Tek. Inform., vol. 7, no. 3, pp. 1238–1254, 2023, doi: 10.33395/sinkron.v8i3.12433.
[13] S. R. Cholil, T. Handayani, R. Prathivi, and T. Ardianita, “Implementasi Algoritma Klasifikasi K-Nearest Neighbor (KNN) Untuk Klasifikasi Seleksi Penerima Beasiswa,” IJCIT (Indonesian J. Comput. Inf. Technol., vol. 6, no. 2, pp. 118–127, 2021.
[14] S. Sumarlin, “Implementasi Algoritma K-Nearest Neighbor Sebagai Pendukung Keputusan Klasifikasi Penerima Beasiswa PPA dan BBM,” J. Sist. Inf. Bisnis, vol. 5, no. 1, pp. 52–62, 2015, doi: 10.21456/vol5iss1pp52-62.
[15] E. Mardiani et al., “Komparasi Metode KNN, Naive Bayes, Decision Tree, Ensemble, Linear Regression Terhadap Analisis Performa Pelajar SMA,” Innov. J. Soc. Sci. Res., vol. 3, no. 2, pp. 13880–13892, 2023, [Online]. Available: http://j-innovative.org/index.php/Innovative/article/view/1949%0Ahttp://j-innovative.org/index.php/Innovative/article/download/1949/1468
[16] S. Maizura, V. Sihombing, and M. H. Dar, “Analysis of the Decision Tree Method for Determining Interest in Prospective Student College,” Sink. J. dan Penelit. Tek. Inform., vol. 7, no. 2, pp. 956–979, 2023, doi: 10.33395/sinkron.v8i2.12258.
[17] B. Charbuty and A. Abdulazeez, “Classification Based on Decision Tree Algorithm for Machine Learning,” J. Appl. Sci. Technol. Trends, vol. 2, no. 01 SE-, pp. 20–28, Mar. 2021, doi: 10.38094/jastt20165.
[18] R. Surya, M. H. Dar, and F. A. Nasution, “Implementation Of Decision Tree Method To Predict Customer Interest In Internet Data Packages,” Int. J. Sci. Technol. Manag., vol. 5, no. 4, pp. 947–952, 2024, doi: 10.46729/ijstm.v5i4.1155.