Analisi Peluang Resign Karyawan Dengan Menggunakan Metode Random Forest: Studi Kasus Pada PT. Top Remit

Adriel, Matthew (2025) Analisi Peluang Resign Karyawan Dengan Menggunakan Metode Random Forest: Studi Kasus Pada PT. Top Remit. Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6032231027-Master_Thesis.pdf Restricted to Repository staff only Download (20MB) | Request a copy

Abstract

Turnover karyawan yang tinggi dapat berdampak negatif terhadap stabilitas dan produktivitas perusahaan, sehingga diperlukan strategi prediktif berbasis data untuk mengidentifikasi faktor-faktor yang memengaruhi keputusan resign karyawan. Penelitian ini bertujuan untuk menganalisis data karyawan PT. Top Remit guna memprediksi kemungkinan resign menggunakan algoritma Random Forest, yang dikenal memiliki kemampuan yang baik dalam menangani data kompleks dan heterogen. Dengan pendekatan machine learning, penelitian ini mengolah data historis karyawan yang mencakup faktor demografi, kepuasan kerja, kompensasi, serta kinerja. Dataset yang digunakan terdiri dari data karyawan yang telah diberi label berdasarkan status pekerjaan. Model Random Forest diterapkan untuk mengidentifikasi pola yang berkontribusi terhadap turnover serta dievaluasi menggunakan metrik accuracy, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa model Random Forest yang telah dioptimalkan melalui hyperparameter tuning menggunakan Grid Search mampu menghasilkan akurasi pengujian sebesar 82,5%, dengan nilai precision kelas resign mencapai 1,00 dan recall sebesar 0,6316. Selain itu, analisis feature importance menunjukkan bahwa faktor yang paling berpengaruh terhadap keputusan resign adalah nilai performa tahunan, average review score, kepuasan kompensasi, kepuasan kerja, dan keterlibatan kerja. Berdasarkan hasil tersebut, perusahaan dapat memanfaatkan model prediksi ini sebagai alat pendukung pengambilan keputusan untuk merancang strategi retensi karyawan yang lebih terarah dan berbasis data. Penelitian ini diharapkan dapat memberikan kontribusi dalam pengembangan analisis prediktif pada manajemen sumber daya manusia, khususnya dalam penerapan metode machine learning untuk mendukung pengelolaan dan keberlanjutan tenaga kerja.
==================================================================================================================================
High employee turnover can negatively affect organizational stability and productivity, making data-driven predictive strategies essential to identify factors influencing employees’ resignation decisions. This study aims to analyze employee data at PT. Top Remit to predict resignation probability using the Random Forest algorithm, which is known for its strong performance in handling complex and heterogeneous data. Using a machine learning approach, this research processes historical employee data that include demographic factors, job satisfaction, compensation, and performance indicators. The dataset consists of labeled employee records based on their employment status. The Random Forest model is applied to identify patterns contributing to employee turnover and is evaluated using performance metrics such as accuracy, precision, recall, and F1-score. The results indicate that the optimized Random Forest model, after hyperparameter tuning using Grid Search, achieves a test accuracy of 82.5%, with a resignation-class precision of 1.00 and a recall value of 0.6316. Furthermore, feature importance analysis reveals that the most influential factors affecting resignation decisions are annual performance scores, average review scores, compensation satisfaction, job satisfaction, and work engagement. Based on these findings, the predictive model can be utilized as a decision-support tool to design more targeted and data-driven employee retention strategies. This study is expected to contribute to the development of predictive analytics in human resource management, particularly in the application of machine learning methods to support workforce management and sustainability

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Machine Learning, Manajemen Sumber Daya Manusia, Prediksi Resign, Random Forest, Turnover Karyawan ======================================================================================================================== Employee Turnover, Human Resource Management, Machine Learning, Random Forest, Resignation Prediction
Subjects:	H Social Sciences > HA Statistics > HA31.3 Regression. Correlation. Logistic regression analysis. H Social Sciences > HF Commerce > HF5549 Job analysis. Personnel management. Employment management
Divisions:	Interdisciplinary School of Management and Technology (SIMT) > 61101-Master of Technology Management (MMT)
Depositing User:	Matthew Adriel
Date Deposited:	19 Jan 2026 04:00
Last Modified:	19 Jan 2026 04:00
URI:	http://repository.its.ac.id/id/eprint/129704

Actions (login required)

View Item