Prediction of Job Seekers’ Career Interests at the Batu Bara Job Training Center (BLK) Based on Individual Characteristics Using Naive Bayes and Decision Tree Algorithms

Abstract

The Batu Bara Job Training Center (Balai Latihan Kerja/BLK) plays an important role in improving workforce competencies through various vocational training programs. However, the diversity of individual characteristics among job seekers often makes it challenging to determine training programs that align with their career interests. This study aims to predict the career interests of job seekers at the Batu Bara Job Training Center based on individual characteristics using machine learning classification methods, namely the Naive Bayes and Decision Tree algorithms. The dataset used in this research consists of job seeker profiles, including demographic attributes, educational background, skills, and work experience. Data preprocessing was conducted through data cleaning, transformation, and feature selection to improve model performance. The classification results were evaluated using accuracy, precision, recall, and F1-score metrics. The findings indicate that both algorithms are capable of predicting job seekers’ career interests effectively, with the Decision Tree algorithm showing slightly better performance compared to Naive Bayes. These results demonstrate that machine learning-based prediction models can support BLK management in providing more targeted and effective training recommendations. The proposed approach is expected to enhance training efficiency and contribute to better workforce placement outcomes.