J. Rolles Herwin Sihombing
Universitas Horizon Indonesia

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Stay or Leave? Predicting Employee Retention With Hybrid Deep Learning Models: Penelitian Yessica Fara Desvia; Wafiqah Yasmin Azhar; Supriyadi Supriyadi; J. Rolles Herwin Sihombing; Nindy Faoziyah
Jurnal Pengabdian Masyarakat dan Riset Pendidikan Vol. 4 No. 4 (2026): Jurnal Pengabdian Masyarakat dan Riset Pendidikan Volume 4 Nomor 4 April - Juni
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jerkin.v4i4.6345

Abstract

Employee retention is a major challenge for organizations in the digital era because high turnover impacts productivity, operational costs, and organizational performance. This study proposes a Hybrid Deep Learning model based on XGBoost and Deep Neural Network (DNN) to predict employee retention using the HR_comma_sep dataset. This approach combines tree-based machine learning and deep learning to capture nonlinear relationships and complex decision patterns. Data preprocessing is performed through feature scaling and categorical encoding before model training. The hybrid architecture is built by integrating the probability outputs of XGBoost and DNN in the meta-classification layer. Evaluation using Accuracy, Precision, Recall, F1-Score, and AUC-ROC shows that the hybrid model has better prediction and generalization performance than conventional methods. SHAP Explainability is used to identify the main factors influencing turnover, namely job satisfaction, average monthly working hours, and length of service. This model can help organizations develop proactive HR management strategies.
Enhancing Learning Effectiveness in Higher Education through Active Learning Approaches Vivi Ayu Lestari; Arif Budimansyah Purba; Ahmad Najib Mutawally; Inpresta Natalia; Gracendy Aluz Clarita; Cepi Indra Grahana; J. Rolles Herwin Sihombing; Juni Adi Putra; Dhanisa Aulia; Ani Suryani
Jurnal Pengabdian Masyarakat dan Riset Pendidikan Vol. 5 No. 1 (2026): Jurnal Pengabdian Masyarakat dan Riset Pendidikan Volume 5 Nomor 1 (Juli 2026 -
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jerkin.v5i1.7437

Abstract

Learning effectiveness in higher education continues to be a significant concern, particularly in learning environments that still rely heavily on lecture-based instruction. Although such approaches allow for efficient content delivery, they often limit student engagement and reduce opportunities for meaningful learning. This study aims to explore how active learning approaches can enhance learning effectiveness from the perspective of university students.A qualitative research design was employed to capture students’ experiences and perceptions of active learning. The study involved university students who participated in learning activities such as group discussions, collaborative tasks, problem-solving exercises, and reflective practices. Data were collected through classroom observations, reflective writings, and semi-structured interviews. The findings indicate that active learning fosters higher levels of engagement, encourages participation, and promotes deeper understanding of learning materials. Students also reported increased confidence in expressing ideas and a greater sense of responsibility toward their learning. In addition, active learning was found to support the development of critical thinking and the ability to connect theoretical concepts with real-life situations.Overall, this study highlights that active learning contributes to more effective and meaningful learning experiences by creating interactive, student-centered environments. It suggests that integrating active learning into higher education can support sustained engagement and improved learning outcomes