Implementasi Metode K-Nearest Neighbor dalam Menentukan Waktu Optimal Penarikan Pesanan Driver Ojol

  • Anton Prasetiyo Universitas Mercu Buana Yogyakarta
Keywords: Keywords: Dataset, Classification, K-Nearest Neighbor, Transportation, Online motorcycle taxi

Abstract

App-based transportation companies are propelling technological advancements in the services provided to every user and online motorcycle taxi partner. Online motorcycle taxis currently represent the most popular and widely used mode of transportation. Thanks to the application system's ability to enable online motorcycle taxi partners to work from anywhere and at any time, an increasing number of individuals are expressing interest in becoming such partners. However, this surge in interest has led to new challenges, particularly regarding income from orders within the competitive landscape of online motorcycle taxi partnerships. Therefore, the author aims to address these issues through this research. Classification algorithms are employed to analyze the optimal timing for processing order requests. This study seeks to develop a classification model using the K-Nearest Neighbor method to determine the optimal timing based on label classes. K-Nearest Neighbor involves identifying k target members in the training data closest to the target in the testing or new data. The dataset utilized in this research is sourced from three online motorcycle taxi driver accounts, comprising a total of 1941 datasets. The classification results using the K-Nearest Neighbor method yielded excellent outcomes, achieving an accuracy level of 99%. Subsequently, testing with a value of k=9 and an 80:20 ratio resulted in an average f1-score of 99.33%.

References

[1] S. Amin, M. Taufiq, and Y. Feriska, “Strategi Pengembangan Jaringan Transportasi Darat Kabupaten Brebes Land Transportation Network Development Strategy of Brebes Regency,” 2021.
[2] D. K. Rahayu and S. Martini, “PERAN MODA TRANSPORTASI DARAT DALAM MOBILITAS TENAGA KERJA,” Jurnal Transportasi, vol. 22, no. 2, pp. 109–116, Aug. 2022, doi: 10.26593/jtrans.v22i2.6061.109-116.
[3] O. Halilintarsyah, “Ojek Online, Pekerja atau Mitra?,” Jurnal Persaingan Usaha, vol. 2, pp. 64–74, Dec. 2021, doi: 10.55869/kppu.v2i.24.
[4] F. N. Anggraeni, “ANALYSIS OF USER SATISFACTION OF PUBLIC TRANSPORTATION OJEK ONLINE (GOJEK) THROUGH SERVICE INSTRUMENTS,” AKADEMIK: Jurnal Mahasiswa Ekonomi & Bisnis, vol. 1, no. 2, pp. 77–86, May 2021, doi: 10.37481/jmeb.v1i2.221.
[5] S. A. Immawati and A. Rauf, “Building satisfaction and loyalty of student users ojek online through the use of it and quality of service in tangerang city,” J Phys Conf Ser, vol. 1477, no. 7, p. 072004, Mar. 2020, doi: 10.1088/1742-6596/1477/7/072004.
[6] Rino Bahtiar, “Implementasi Data Mining Untuk Prediksi Penjualan Kusen Terlaris Menggunakan Metode K-Nearest Neighbor,” Jurnal Informatika Multi, vol. 1, no. 3, pp. 203–214, May 2023, [Online]. Available: https://jurnal.publikasitecno.id/index.php/multi/article/view/33
[7] A. Aisyah and S. Anraeni, “Analisis Penerapan Metode K-Nearest Neighbor (K-NN) pada Dataset Citra Penyakit Malaria,” Indonesian Journal of Data and Science, vol. 3, no. 1, pp. 17–29, Mar. 2022, doi: 10.56705/ijodas.v3i1.22.
[8] R. Wahyudi, M. Orisa, and N. Vendyansyah, “PENERAPAN ALGORITMA K-NEAREST NEIGHBORS PADA KLASIFIKASI PENENTUAN GIZI BALITA (STUDI KASUS DI POSYANDU DESA BLUTO),” JATI (Jurnal Mahasiswa Teknik Informatika), vol. 5, no. 2, pp. 750–757, Oct. 2021, doi: 10.36040/jati.v5i2.3738.
[9] D. P. Utomo and M. Mesran, “Analisis Komparasi Metode Klasifikasi Data Mining dan Reduksi Atribut Pada Data Set Penyakit Jantung,” JURNAL MEDIA INFORMATIKA BUDIDARMA, vol. 4, no. 2, p. 437, Apr. 2020, doi: 10.30865/mib.v4i2.2080.
[10] R. Annisa, “ANALISIS KOMPARASI ALGORITMA KLASIFIKASI DATA MINING UNTUK PREDIKSI PENDERITA PENYAKIT JANTUNG,” JTIK (Jurnal Teknik Informatika Kaputama), vol. 3, no. 1, pp. 22–28, Jan. 2019, doi: 10.59697/jtik.v3i1.650.
[11] Y. Azhar, A. K. Firdausy, and P. J. Amelia, “Perbandingan Algoritma Klasifikasi Data Mining Untuk Prediksi Penyakit Stroke,” SINTECH (Science and Information Technology) Journal, vol. 5, no. 2, pp. 191–197, Oct. 2022, doi: 10.31598/sintechjournal.v5i2.1222.
[12] Alfian Adam, “Data Preprocessing: Pengertiann Manfaat, dan Tahapan kerjanya,” Accurate. Accessed: Apr. 27, 2024. [Online]. Available: https://accurate.id/teknologi/data-preprocessing/
[13] Andre Oliver, “Bikin Data Lebih Mudah Dibaca, yuk, Kenalan dengan Data Preprocessing,” glints. Accessed: Apr. 27, 2024. [Online]. Available: https://glints.com/id/lowongan/data-preprocessing-adalah/
[14] Fahmi Noor Fiqri, “Klasifikasi Bunga Iris Menggunakan KNN Phyton,” Kodesiana. Accessed: May 03, 2024. [Online]. Available: https://www.kodesiana.com/post/klasifikasi-bunga-iris-menggunakan-knn-python/
[15] Siti Khadijah Azzukhruf Firdausi, “Data Preprocessing Adalah: Pengertian, Manfaat, & Tahapannya,” Dibimbing. Accessed: Apr. 27, 2024. [Online]. Available: https://dibimbing.id/blog/detail/data-preprocessing-adalah-pengertian-manfaat-tahapannya
[16] K. M. Rajabi, W. Witanti, and R. Yuniarti, “Penerapan Algoritma K-Nearest Neighbor (KNN) Dengan Fitur Relief-F Dalam Penentuan Status Stunting,” Innovative: Journal Of Social Science Research, vol. 3, no. 4, pp. 3555–3568, Sep. 2023, doi: 10.31004/innovative.v3i4.3885.
[17] Eka Anzihory, “Normalisasi vs Standarisasi,” Medium. Accessed: May 03, 2024. [Online]. Available: https://anzihory.medium.com/normalisasi-vs-standarisasi-101093633e18
[18] A. A. P. Tanggu Mara, E. Sediyono, and H. Purnomo, “K-Nearest Neighbors Algorithm to Student Opinion of the Online Learning Method at Wira Wacana Sumba Christian University,” Ultima InfoSys : Jurnal Ilmu Sistem Informasi, pp. 87–93, Apr. 2022, doi: 10.31937/si.v12i2.2090.
[19] A. K. B. Ginting, M. S. Lydia, and E. M. Zamzami, “Peningkatan Akurasi Metode K-Nearest Neighbor dengan Seleksi Fitur Symmetrical Uncertainty,” JURNAL MEDIA INFORMATIKA BUDIDARMA, vol. 5, no. 4, p. 1714, Oct. 2021, doi: 10.30865/mib.v5i4.3254.
[20] G. M. C. Batubara, A. Desiani, and A. Amran, “Klasifikasi Jamur Beracun Menggunakan Algoritma Naïve Bayes dan K-Nearest Neighbors,” Jurnal Ilmu Komputer dan Informatika, vol. 3, no. 1, pp. 33–42, Jun. 2023, doi: 10.54082/jiki.68.
Published
2024-06-10