MACHINE LEARNING FOR EMPLOYMENT POSITION MAPPING - predictive HR analytics with Bagged Decision Tree

Aug 3, 2026

Employee performance directly determines organizational efficiency, yet conventional HR analytics often fall short in predictive accuracy. This study connects human resource theory with machine learning by evaluating tree-based models for employee data analysis. Using 15,227 employee records, Bagged Decision Tree achieves 98.65% accuracy, identifying talent and career values as key predictors. Removing aspiration features slightly lowers accuracy, while removing career values sharply reduces performance prediction quality. Results support robust HR predictive analytics and stress careful variable selection for reliable outcomes.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Introduction

Human capital and organizational behavior foundation

Machine learning and predictive modeling approach

Data mining and common predictive methods

MACHINE LEARNING FOR EMPLOYMENT POSITION MAPPING Sena Aditia Apriadi1*; Hilman Ferdinandus Pardede2 Computer Science1 Universitas Muhammadiyah Kuningan, Kuningan, Indonesia1 [https://umkuningan.ac.id/](https://umkuningan.ac.id/) Research Center for ArtiﬁcialIntelligence and Cybersecurity2 National Research and Innovation Agency (BRIN), Jakarta Pusat, Indonesia 2 [https://www.brin.go.id/](https://www.brin.go.id/) [shevana7@gmail.com](shevana7@gmail.com1)[1](shevana7@gmail.com1)*, [hilman@nusamandiri.ac.id](hilman@nusamandiri.ac.id2)[2](hilman@nusamandiri.ac.id2) (*) Corresponding Author The creation is distributed under the Creative Commons Attribution-NonCommercial 4.0 International License. Abstract—Employee performance directly impacts organizational efficiency, yet traditional HR analyticsoften lack predictive precision. This study bridges HR theory and machine learning by evaluating treebased algorithms for employee data analysis. Using adataset of 15,227 employee records, we tested the Bagged Decision Tree algorithm, focusing on variables such as talent, career values, and aspirations. The Bagged Decision Tree achieved 98.65% accuracy, with talent and career values as key predictors. Excluding aspiration values reduced accuracy slightly to 98.57%, while excluding career values lowered it significantly to 92.13%. These findings highlight the robustness of the Bagged Decision Tree in HR analytics and emphasize the importance of variable selection, particularly career values and talent, in predicting performance outcomes. Future work should further explore realworld implementation challenges. Keywords: bagged decision tree, employees, machine learning, organizational performance, predictive analytics. Abstrak—Kinerjapegawai berperan penting dalam menentukan efisiensi organisasi, namun analitik SDM tradisional sering kali belum mampu memberikan prediksi yang akurat. Studi ini menjembatani teori SDM dengan machine learning melalui evaluasi algoritma berbasis pohon keputusandalam menganalisis data pegawai. Menggunakan data dari 15.227 pegawai, algoritma Bagged Decision Tree diuji dengan menyoroti variabel talenta, nilai karier, dan aspirasi. Algoritma ini mencapai akurasi 98,65%, dengan talenta dan nilai karier sebagai prediktor utama. Penghapusanvariabel aspirasi menurunkan akurasi menjadi 98,57%, sedangkan tanpa variabel nilai karier akurasi turun hingga 92,13%. Temuan ini menegaskan keandalan Bagged Decision Tree dalamanalitik SDM dan menunjukkan pentingnyapemilihan variabel, khususnya nilai karier dan talenta, dalam memprediksi kinerja pegawai. Penelitian selanjutnya perlu menggali implementasi di dunia nyata beserta tantangan yang mungkindihadapi. Kata Kunci: analitik prediktif, bagged decision tree, kinerja organisasi, machine learning, pegawai. INTRODUCTION Grounded in the human capital theory, which emphasizes employees as pivotal organizational assets, this study examines the role of employee attributes in achieving operational excellence and evaluates the effectiveness of predictive algorithms for talent management. This research employs a tree-based machine learning approach, guided by theoretical principles from decision-making and organizational behavior, to analyze a dataset of 15,227 employees and identify critical factors influencing performance outcomes. Employees provide their physical and intellectual capabilities to the organization in return for compensation determined through mutual agreements and organizational policies. Higher employee competence enhances the organization’s ability to achieve sustainable competitive advantage (Kang & Lee, 2021) . Employees are also physical and spiritual human labor (mental and mind) that are needed, therefore employees become the main capital in a company or organization to achieve the goals or vision and mission of the company (Rahimiet al., 2025). In the big dictionary of Indonesian, the meaning of position is a job or task in government

FAQs

What problem does the study address in HR analytics?

Traditional HR analytics often lack predictive precision when estimating employee-related performance outcomes. The study aims to improve prediction accuracy using machine learning.

Which algorithm is used and what accuracy does it achieve?

The study tests the Bagged Decision Tree algorithm on 15,227 employee records and reports 98.65% accuracy.

How do different variables affect prediction performance?

Talent and career values are identified as key predictors. Excluding aspiration values slightly reduces accuracy, while excluding career values causes a much larger drop to 92.13%.

Aug 3, 2026

Upload by Seraphina