A Systematic Review of Random Forest and Logistic Regression Algorithms for Predicting Student Readiness in LSP-P1 Competency Certification at Vocational High Schools

Abstract

Assessing student readiness for LSP-P1 Competency Certification in Indonesian vocational schools is still commonly performed manually, resulting in subjective and potentially inaccurate decisions. Although existing studies have applied machine learning algorithms such as Random Forest and Logistic Regression to predict academic performance, limited research specifically focuses on vocational certification readiness within the Indonesian LSP-P1 context. This study applies a Systematic Literature Review (SLR) following Kitchenham and Charters guidelines to examine research trends, predictor variables, and key findings from previous studies. The review reveals that both algorithms are promising for readiness prediction; however, no study has explicitly addressed their application for LSP-P1 readiness at the SMK level. This work identifies research gaps and highlights opportunities for future development of data-driven decision support systems.