APPLICATION OF MACHINE LEARNING IN PREDICTING EMPLOYEE DISCIPLINE VIOLATIONS IN FINANCIAL SERVICE COMPANY

Muhamad Fadel; Kanasfi Kanasfi; Arief  Wibowo

doi:10.52436/1.jutif.2024.5.1.1229

Muhamad Fadel Master of Computer Science, Information and Technology Faculty Universitas Budi Luhur, Indonesia
Kanasfi Master of Computer Science, Information and Technology Faculty Universitas Budi Luhur, Indonesia
Arief Wibowo Master of Computer Science, Information and Technology Faculty Universitas Budi Luhur, Indonesia

DOI: https://doi.org/10.52436/1.jutif.2024.5.1.1229

Keywords: Decision Tree, Machine Learning, Majority Voting, Naïve Bayes, Random Forest

Abstract

Employee compliance is a commitment to comply with regulations and stay away from matters that are prohibited in the laws and or company regulations which if not obeyed, then employees are given disciplinary sanctions. Employee discipline is an obligation and willingness of employees in obeying all existing rules in a company to achieve its vision and mission, a high-level employee disciplinary violation rate of 38% at PT. HCI who are engaged in financial service sector can have a negative impact on a company's reputation, meanwhile a low level of employee disciplinary violations in a company can have a positive impact on the company's reputation.This paper aims to predict the possibility of employees committing discipline violations and evaluating the performance of accuracy by using Machine Learning Random Forest, Decision Tree, and Naive Bayes techniques. The test results prove that the Machine Learning Random Forest technique is the best model with the highest value in terms of accuracy with a value of 87.30%, while the Machine Learning Decision Tree and Naive Bayes technique has a value of 83.28%and 70.27% respectively, the value from each of the Machine Learning techniques, the comparison was made using majority voting techniques, so as to produce a total accuracy value of 85.31%.With this high accuracy value, the Random Forest model is proven to have better performance individually in analyzing the prediction of disciplinary violations in the application of human resources at company, while the total accuracy value uses a majority voting model of 85.31%, slightly decreased due to the high level of accuracy of the Naïve Bayes model compared to other algorithm models.

Downloads

Download data is not yet available.

References

R. Sistem, A. Wibowo, M. Makruf, I. Virdyna, and F. C. Venna, “Penentuan Klaster Koridor TransJakarta dengan Metode Majority Voting,” vol. 1, no. 10, pp. 565–575, 2021.

A. Pratama et al., “Jurnal Smart Teknologi Penerapan Teknik Vote Menggunakan C4 . 5 Naïve Bayes Dan K-nearest Neighbor Pada Data Gangguan Autisme Application of Vote Technique Using C4 . 5 Naïve Bayes and K-nearest Neighbor on Autism Disorder Data Jurnal Smart Teknologi,” vol. 3, no. 6, pp. 638–645, 2022.

D. R. Utari and A. Wibowo, “Pemodelan Prediksi Status Keberlanjutan Polis Asuransi Kendaraan dengan Teknik Pemilihan Mayoritas Menggunakan Algoritma-Algoritma Klasifikasi Data Mining,” vol. 5, no. 2502, pp. 19–24, 2020, doi: 10.22236/teknoka.v5i.391.

L. Iryani, “Penerapan Machine Learning Dalam Klasifikasi Kinerja Pegawai Pt X,” J. Informanika, vol. 09, no. 01, pp. 1–6, 2023, doi: https://doi.org/10.52233/informanika.v9i01.391.

V. Skrbinjek and V. Dermol, “Predicting students’ satisfaction using a decision tree,” no. 1994, 2019.

S. Maji and S. Arora, Decision Tree Algorithms for Prediction of Heart Disease. Springer Singapore, 2019. doi: 10.1007/978-981-13-0586-3.

K. Khotimah, “Teknik Data Mining menggunakan Algoritma Decision Tree (C4.5) untuk Prediksi Seleksi Beasiswa Jalur KIP pada Universitas Muhammadiyah Kotabumi,” J. SIMADA (Sistem Inf. dan Manaj. Basis Data), vol. 4, no. 2, pp. 145–152, 2022, doi: 10.30873/simada.v4i2.3064.

P. Sonar and K. Jayamalini, “Diabetes Prediction Using Different Machine Learning Approaches,” 2019 3rd Int. Conf. Comput. Methodol. Commun., no. Iccmc, pp. 367–371, 2019.

M. Hasan, “Prediksi Tingkat Kelancaran Pembayaran Kredit Bank Menggunakan Algoritma Naive Bayes Berbasis Forward Selection,” vol. 9, pp. 317–324, 2017.

C. A. S. Tri Herdiawan Apandi, “Algoritma Naive Bayes untuk Prediksi Kepuasan Pelayanan Perekaman e-KTP,” JUITA J. Inform. e-ISSN 2579-9801, Vol. 7, Nomor 2, vol. 7, 2019.

M. Syukri Mustafa, M. Rizky Ramadhan, and A. P. Thenata, “Implementasi Data Mining untuk Evaluasi Kinerja Akademik Mahasiswa Menggunakan Algoritma Naive Bayes Classifier,” Citec J., vol. 4, no. 2, pp. 151–162, 2017.

J. Sanjaya, E. Renata, V. E. Budiman, F. Anderson, and M. Ayub, “Prediksi Kelalaian Pinjaman Bank Menggunakan Random Forest dan Adaptive Boosting,” vol. 6, no. April, pp. 50–60, 2020.

T. Online, S. Kasus, D. Acak, P. Awal, and M. Pandemic, “Jurnal Politeknik Caltex Riau Prediksi Harga Bitcoin Menggunakan Metode Random Forest,” vol. 7, no. 1, pp. 24–32, 2021.

H. Nalatissifa, W. Gata, S. Diantika, and K. Nisa, “Perbandingan Kinerja Algoritma Klasifikasi Naive Bayes , Support Vector Machine ( SVM ), dan Random Forest untuk Prediksi Ketidakhadiran di Tempat Kerja,” vol. 5, no. 4, pp. 578–584, 2021.

W. Apriliah, I. Kurniawan, M. Baydhowi, and T. Haryati, “SISTEMASI: Jurnal Sistem Informasi Prediksi Kemungkinan Diabetes pada Tahap Awal Menggunakan Algoritma Klasifikasi Random Forest,” J. Sist. Inf., vol. 10, pp. 163–171, 2021, [Online]. Available: http://sistemasi.ftik.unisi.ac.id.