Aplikasi Penilaian Kinerja Karyawan Menggunakan Metode Algoritma Bayesian Classifier Pada PT. Cipta Anugerah Musi

Sihite, Janssen Alfonso (2025) Aplikasi Penilaian Kinerja Karyawan Menggunakan Metode Algoritma Bayesian Classifier Pada PT. Cipta Anugerah Musi. Undergraduate thesis, Universitas Musi Katolik Charitas.

[img] Text (IF-2025-2013007-summary_id)
IF-2025-2013007-summary_id.pdf
Restricted to Registered users only

Download (361kB) | Request a copy
[img] Text (IF-2025-2013007-complete)
IF-2025-2013007-complete.pdf
Restricted to Repository staff only

Download (3MB) | Request a copy

Abstract

Employee performance assessment is an important step in ensuring company productivity. PT. Cipta Anugerah Musi has so far still used manual methods with limited criteria, so the results are less accurate. This research develops an employee performance assessment application using the Naive Bayes algorithm, which utilizes seven main criteria: personality, obeying rules, discipline, responsibility, thoroughness, productivity and neatness. Test results show that this application is able to predict employee performance assessments with an accuracy level of 86.67%, an average precision of 82%, and an average recall of 82%. This application has proven effective in increasing the efficiency of the employee performance appraisal process while reducing manual errors. Thus, the implementation of the Naive Bayes algorithm in this application has succeeded in becoming a reliable tool for HRD in making decisions regarding employee performance assessment. Keywords: Employee Performance Assessment, Performance Appraisal Application, Naïve Bayes Algorithm.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Employee Performance Assessment, Performance Appraisal Application, Naïve Bayes Algorithm.
Subjects: T Technology > T Technology (General)
Divisions: Theses - S1 > Informatics Study Program
Depositing User: Janssen Alfonso Sihite
Date Deposited: 07 Mar 2025 05:04
Last Modified: 07 Mar 2025 05:04
URI: http://eprints.ukmc.ac.id/id/eprint/13645

Actions (login required)

View Item View Item