DECISION SUPPORT SYSTEM FOR PREDICTING EMPLOYEE LEAVE USING THE LIGHT GRADIENT BOOSTING MACHINE (LIGHTGBM) AND K-MEANS ALGORITHM

Vasthu Imaniar  Ivanoti; Megananda Hervita P.; Gandung Triyono; Dyah Puji Utami

doi:10.52436/1.jutif.2023.4.3.1084

Vasthu Imaniar Ivanoti Master of Computer Science, Faculty of Information Technology, Universitas Budi Luhur, Indonesia
Megananda Hervita P. Master of Computer Science, Faculty of Information Technology, Universitas Budi Luhur, Indonesia
Gandung Triyono Master of Computer Science, Faculty of Information Technology, Universitas Budi Luhur, Indonesia
Dyah Puji Utami Faculty of Engineering, Architecture & Information Technology, The University of Queensland, Australia

DOI: https://doi.org/10.52436/1.jutif.2023.4.3.1084

Keywords: decision support system, employee leave, k-means clustering, light gradient boosting machine

Abstract

Nowadays, decision support systems have gained wide popularity not only in private companies but also in government sectors. These systems play a crucial role in assisting leaders during the decision-making process. The effective functioning of the government heavily relies on employee performance, which requires discipline in carrying out their duties and responsibilities. Employee discipline is closely linked to their attendance, including leave-taking. Therefore, analyzing employee leave data can reveal trends and interrelationships, providing leaders with valuable information and insights for determining employee leave policies. To address this issue, data mining applications such as the Light Gradient Boosting Machine (LightGBM) regression prediction model can be utilized. This model takes into account factors like gender, age, and the starting year of leave to predict the number of employees who take annual leave simultaneously with holidays. Additionally, clustering algorithms like K-Means can be employed to group reasons for leave into clusters, identifying common leave patterns among employees. In this study, employee leave application data from January 2018 to July 2022 was collected from the Leave module within the HRIS (Human Resource Information System) application. The research outcomes encompass a dashboard visualization presenting descriptive analysis and modeling using LightGBM. The modeling results yielded reasonably accurate predictions, as evidenced by model testing that showed a difference of only 1 employee. Additionally, K-Means clustering formed 4 clusters of leave reasons, with the majority being family-related, illness, childcare, and elderly care. The dashboard can be used by management as a consideration for approving employee leaves, ensuring well-planned leave scheduling for the following year and minimizing disruption to work execution in each department.

Downloads

Download data is not yet available.

References

I. Mardeli and Y. Yansahrita, “Pengaruh Kedisiplinan Terhadap Prestasi Kerja Pegawai Pada Kantor Kecamatan Belitang Madang Raya Oku Timur,” J. Aktual STIE Trisna Negara, vol. 17, no. 1, pp. 41–52, 2019, doi: 10.47232/aktual.v17i1.32.

K. Ummi, Daifiria, and Irwansyah, “Penerapan Metode Deskripsi Pada Sistem Monitoring Data Cuti Pegawai Di Dinas Pemerintahan,” CSRID J., vol. 13, no. 3A, pp. 190–200, 2021.

Peraturan Badan Kepegawaian Negara Republik Indonesia Nomor 24 Tahun 2017 tentang Tata Cara Pemberian Cuti Pegawai Negeri Sipil. Jakarta: Badan Kepegawaian Negara, 2017.

M. I. Dwipayani, A. S. Honggowibowo, and D. Nugraheny, “Sistem Pendukung Keputusan Penentuan Cuti Pegawai Menggunakan Metode Technique For Order Preference By Similarity To Ideal Solution (TOPSIS),” Compiler, vol. 1, no. 1, pp. 47–61, 2012, doi: http://dx.doi.org/10.28989/compiler.v1i1.5.

A. F. A. Natsir and M. K. Najiyah, Ina S.Kom., “Sistem Pendukung Keputusan Cuti Pegawai Di PUSDIKKU TNI AD dengan Menggunakan Metode SAW Berbasis Web,” eProsiding Tek. Inform., vol. 2, no. 1, pp. 21–27, 2021.

M. K. Zuhri, L. Yulianti, and R. Supardi, “The Implementation of SAW Method in Applying Employees Leave At The Regional Secretariat Office Of Bengkulu,” J. Komput. Indones., vol. 1, no. 1, pp. 43–48, 2022, [Online]. Available: https://jurnal-unived.com/index.php/JK/article/view/12

C. S. Suriady, L. P. Dewi, and A. Setiawan, “Aplikasi Human Resource Information System dengan Fitur Sistem Pendukung Keputusan (Studi Kasus PT. Industri Kreatif Digital),” J. Infra, vol. 9, no. 2, pp. 314–319, 2021, [Online]. Available: http://publication.petra.ac.id/index.php/teknik-informatika/article/view/11466%0Ahttps://publication.petra.ac.id/index.php/teknik-informatika/article/download/11466/10076

T. P. Putri and Febriani, “Clustering Data Cuti Sakit Menggunakan Algoritma Affinity Propagation (Studi Kasus: Perusahaan Telekomunikasi Di Jakarta),” J. Ilm. Teknol. dan Rekayasa, vol. 27, no. 1, pp. 69–84, 2022, doi: http://dx.doi.org/10.35760/tr.2022.v27i1.5823.

Y. Hermawan, A. Mulyana, and N. F. Rizky I., “Rancang Bangun Sistem Informasi Kepegawaian Berbasis Web di STIE Kesatuan,” JAS-PT (Jurnal Anal. Sist. Pendidik. Tinggi Indones., vol. 3, no. 2, pp. 153–160, 2019, doi: 10.36339/jaspt.v3i2.420.

D. A. Firmansah, R. S. Rohman, and Y. Farlina, “Aplikasi Website Pengajuan Cuti Karyawan Rumah Sakit Islam Assyifa Sukabumi Berbasis Whatsapp Blast,” J. Teknol. dan Inf., vol. 10, no. 2, pp. 129–143, 2020, doi: 10.34010/jati.v10i2.2854.

R. Taufiq, A. A. Permana, and M. A. Marfino, “Rancang Bangun Sistem Informasi Pengajuan Cuti Berbasis Web Pada Pt. Tribuana Gasindo,” JIKA (Jurnal Inform. Univ. Muhammadiyah Tangerang, vol. 6, no. 1, pp. 99–104, 2022, doi: 10.31000/jika.v6i1.5472.

M. Badrul and L. N. Janah, “Penerapan Metode Waterfall dalam Sistem Informasi Cuti Kepegawaian Madrasah Istiqlal,” J. Sains Komput. Inform. (J-SAKTI, vol. 6, no. 1, pp. 282–293, 2022, doi: 10.30645/j-sakti.v6i1.444.

M. A. Rizaldi and A. Primajaya, “Rancang Bangun Sistem Informasi Pengajuan Cuti Pegawai Berbasis Web pada PT. Mitratiga Perkasa Abadi,” J. Ilm. Wahana Pendidik., vol. 8, no. 16, pp. 381–388, 2022, doi: 10.5281/zenodo.7067874.

A. Rachman and Effiyaldi, “Sistem Informasi Cuti Pegawai Berbasis Web Pada Universitas Jambi,” Manaj. Sist. Inf., vol. 8, no. 1, pp. 55–66, 2023, doi: https://doi.org/10.33998/jurnalmsi.2023.8.1.763.

C. A. Gemawaty, “Perancangan Sistem Pengajuan Cuti Kerja PT DCM Fatih Medika Menggunakan Netbeans,” Innov. J. Soc. Sci. Res., vol. 2, no. 2, pp. 95–101, 2022, doi: https://doi.org/10.31004/innovative.v2i2.80.

J. Yang et al., “Brief introduction of medical database and data mining technology in big data era,” J. Evid. Based. Med., vol. 13, pp. 57–69, 2020, doi: 10.1111/jebm.12373.

F. Martinez-Plumed et al., “CRISP-DM Twenty Years Later : From Data Mining Processes to Data Science Trajectories,” IEEE Trans. Knowl. Data Eng., vol. 33, no. 8, pp. 3048–3061, 2019, doi: 10.1109/TKDE.2019.2962680.

D. A. Nasution, H. H. Khotimah, and N. Chamidah, “Perbandingan Normalisasi Data untuk Klasifikasi Wine Menggunakan Algoritma K-NN,” J. Comput. Eng. Syst. Sci., vol. 4, no. 1, pp. 78–82, 2019, doi: 10.24114/cess.v4i1.11458.

F. M. Hana, “Klasifikasi Penderita Penyakit Diabetes Menggunakan Algoritma Decision Tree C4.5,” J. SISKOM-KB (Sistem Komput. dan Kecerdasan Buatan), vol. 4, no. 1, pp. 32–39, 2020, doi: 10.47970/siskom-kb.v4i1.173.

A. A. Aldino, D. Darwis, A. T. Prastowo, and C. Sujana, “Implementation of K-Means Algorithm for Clustering Corn Planting Feasibility Area in South Lampung Regency,” J. Phys. Conf. Ser., vol. 1751, no. 1, 2021, doi: 10.1088/1742-6596/1751/1/012038.

E. Buulolo, Data Mining Untuk Perguruan Tinggi. Deepublish, 2020. [Online]. Available: https://books.google.co.id/books?id=-K%5C_SDwAAQBAJ

M. K. Pangkasidhi, H. N. Palit, and A. Gunawan, “Analisis Sentimen Mahasiswa di Surabaya Terhadap Pelayanan Vaksinasi COVID-19 Menggunakan Beberapa Classifier,” J. Infra, vol. 10, no. 2, pp. 21–27, 2022.

Y. Zhang, C. Zhu, and Q. Wang, “LightGBM-based model for metro passenger volume forecasting,” IET Intell. Transp. Syst., vol. 14, no. 13, pp. 1815–1823, 2020, doi: 10.1049/iet-its.2020.0396.

P. Septiana Rizky, R. Haiban Hirzi, and U. Hidayaturrohman, “Perbandingan Metode LightGBM dan XGBoost dalam Menangani Data dengan Kelas Tidak Seimbang,” J Stat., vol. 15, no. 2, pp. 228–236, 2022, doi: https://doi.org/10.36456/jstat.vol15.no2.a5548.

D. N. P. Sari and Y. Sukestiyarno, “Analisis Cluster dengan Metode K-Means pada Persebaran Kasus Covid-19 Berdasarkan Provinsi di Indonesia,” Prism. Pros. Semin. Nas. Mat., vol. 4, pp. 602–610, 2021, [Online]. Available: https://journal.unnes.ac.id/sju/index.php/prisma/

E. Umargono, J. E. Suseno, and V. G. S. K., “K-Means Clustering Optimization using the Elbow Method and Early Centroid Determination Based-on Mean and Median,” Proc. 2nd Int. Semin. Sci. Technol. (ISSTEC 2019), vol. 1, pp. 234–240, 2019, doi: 10.5220/0009908402340240.

R. Y. Sari, H. Oktavianto, and H. W. Sulistyo, “Algoritma K-Means dengan Metode Elbow untuk Mengelompokkan Kabupaten/Kota di Jawa Tengah Berdasarkan Komponen Pembentuk Indeks Pembangunan Manusia,” J. Smart Teknol., vol. 3, no. 2, pp. 104–108, 2022, [Online]. Available: http://jurnal.unmuhjember.ac.id/index.php/JST/article/view/6928

V. A. Permadi, S. P. Tahalea, and R. P. Agusdin, “K-Means and Elbow Method for Cluster Analysis of Elementary School Data,” Prog. Pendidik., vol. 4, no. 1, pp. 50–57, 2023, doi: 10.29303/prospek.v4i1.328.

K. R. Shahapure and C. Nicholas, “Cluster quality analysis using silhouette score,” Proc. - 2020 IEEE 7th Int. Conf. Data Sci. Adv. Anal., pp. 747–748, 2020, doi: 10.1109/DSAA49011.2020.00096.

R. Hidayati, A. Zubair, A. H. Pratama, and L. Indana, “Analisis Silhouette Coefficient pada 6 Perhitungan Jarak K-Means Clustering,” Techno.COM, vol. 20, no. 2, pp. 186–197, 2021, doi: 10.33633/tc.v20i2.4556.

C. Dr. Meiryani, S.E., Ak., M.M., M.Ak., “Memahami R Square (Koefisien Determinasi) Dalam Penelitian Ilmiah,” 2021. https://accounting.binus.ac.id/2021/08/12/memahami-r-square-koefisien-determinasi-dalam-penelitian-ilmiah/ (accessed May 26, 2023).