NUGROHO, Dafiz Adi and Widodo, Catur Edi and Gernowo, Rahmat (2023) ANALISIS KOMBINASI METODE ANALYTICAL HIERARCHY PROCESS, DECISION TREE C 4.5, DAN PARTICLE SWARM OPTIMIZATION PADA SISTEM INFORMASI KLASIFIKASI PEGAWAI. Masters thesis, UNIVERSITAS DIPONEGORO.

	Text HAL PENDAHULUAN 30000320420048_Dafiz Adi Nugroho.pdf Download (3MB)
	Text BAB 1 30000320420048_Dafiz Adi Nugroho.pdf Download (634kB)
	Text BAB 2 30000320420048_Dafiz Adi Nugroho.pdf Download (712kB)
	Text BAB 3 30000320420048_Dafiz Adi Nugroho.pdf Restricted to Repository staff only Download (1MB)
	Text BAB 4 30000320420048_Dafiz Adi Nugroho.pdf Restricted to Repository staff only Download (1MB)
	Text BAB 5 30000320420048_Dafiz Adi Nugroho.pdf Download (624kB)
	Text DAFTAR PUSTAKA 30000320420048_Dafiz Adi Nugroho.pdf Download (707kB)
	Text LAMPIRAN 30000320420048_Dafiz Adi Nugroho.pdf Restricted to Repository staff only Download (2MB)

Abstract

Klasifikasi pegawai digunakan dalam pemilihan pegawai yang layak untuk promosi jabatan, klasifikasi pegawai salah satunya dapat dilakukan dengan menggunakan algoritma Decision Tree C4.5. Decision Tree C4.5 banyak diimplementasikan dalam berbagai bidang penelitian dalam menentukan klasifikasi, tetapi masih terdapat kelemahan pada Decision Tree C4.5, salah satunya tidak dapat melakukan pemeringkatan pada setiap alternatif. Pada penelitian ini, untuk mengatasi kelemahan dari Decision Tree C4.5 tersebut, diusulkan kombinasi metode Analytical Hierarchy Process (AHP), Decision Tree C4.5, dan Particle Swarm Optimization (PSO) pada studi kasus klasifikasi pegawai untuk rekomendasi promosi jabatan. Penelitian dimulai dengan menentukan kriteria dan bobot kriteria dari hasil wawancara yang kemudian diproses dengan AHP untuk menghasilkan peringkat pegawai dan label kelayakan untuk proses klasifikasi. Proses klasisikasi menggunakan metode Decision Tree C4.5 yang dioptimasi dengan algoritma PSO sehingga menhasilkan data kelayakan pegawai untuk promosi jabatan. Hasil dari penilitian kombinasi metode AHP, Decision Tree C4.5, dan PSO menunjukkan bahwa AHP dapat menghasilkan peringkat pegawai berdasarkan kriteria kinerja dan potensi, dan klasifikasi Decision Tree C4.5 dan optimasi dengan PSO mempunyai hasil akurasi yang lebih baik yaitu 89,67 % dibandingkan dengan metode Decision Tree C4.5 tanpa optimasi PSO yaitu 75 %. Berdasarkan hasil pemeringkatan dan klasifikasi dari penelitian ini dapat digunakan sebagai dasar promosi jabatan pegawai.
Kata Kunci : AHP, C4.5, PSO, klasifikasi pegawai

Employee classification is used in selecting employees who are eligible for promotion, one of which is employee classification can be done using the Decision Tree C4.5 algorithm. Decision Tree C4.5 has been widely implemented in various fields of research in determining classification, but there are still weaknesses in Decision Tree C4.5, one of which is not being able to rank each alternative. In this study, to overcome the weaknesses of Decision Tree C4.5, a combination of the Analytical Hierarchy Process (AHP), Decision Tree C4.5, and Particle Swarm Optimization (PSO) methods is proposed in a case study of employee classification for promotion recommendations. The research begins by determining the criteria and criteria weights from the results of interviews which are then processed by the AHP to produce employee ratings and eligibility labels for the classification process. The classification process uses the Decision Tree C4.5 method which is optimized with the PSO algorithm to produce employee eligibility data for promotion. The results of the research on the combination of AHP, Decision Tree C4.5, and PSO methods show that AHP can produce employee ratings based on performance and potential criteria, and Decision Tree C4.5 classification and optimization with PSO have better accuracy results, namely 89,67% compared to the Decision Tree C4.5 method without PSO optimization is 75%. Based on the results of the ranking and classification of this study can be used as a basis for promotion of employee positions.
Keywords : AHP, C4.5, PSO, Employee classification

Actions (login required)

View Item