Prediksi Promosi Pegawai Menggunakan Metode Extremely Randomized Trees
Keywords:
Extremely Randomized Trees, Employee Promotion, Machine LearningAbstract
With the advancement of information technology and data analytics, new opportunities arise in decision-making within the field of human resources. The implementation of ensemble methods, such as extremely randomized trees, holds promise in predicting promotion decisions with higher accuracy. Despite numerous studies in this domain, there is a need for a deeper exploration in adapting ensemble methods to the context of employee promotions, considering various factors like skills, experience, and individual achievements. This research aims to develop an effective predictive model for employee promotions by integrating extremely randomized trees with relevant human resources data.
The model derived from this study achieved an accuracy rate of 99% on the training data, indicating highly precise predictions. The use of test data confirmed the model's performance with an accuracy score of 98%, illustrating its consistent predictive capabilities. Factors such as avg_training_score, department, total_score, age, and sum_metric were identified as the most influential in shaping the model, providing crucial insights for human resources management.
Downloads
Published
Issue
Section
License
Authors who publish with this journal agree to the following terms:
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
