Predicting Optimal Improvement Priorities for Remote Driving Technology Vocational Education Quality: A Random Forest-Based Predictive Framework
Year: 2025
Type: conference-paper
Abstract: The rapid advancement of autonomous driving technology has created urgent demands for high-quality remote driving technology vocational education programs, yet educational institutions struggle to identify optimal improvement priorities in this emerging field. This study develops a Random Forest-based predictive framework to assess educational quality and determine optimal improvement priorities for remote driving technology vocational education. We employed Random Forest ensemble learning with 300 decision trees to analyze survey data from 2,248 stakeholders including 1,847 students, 312 instructors, and 89 industry professionals across 15 vocational institutions in China. The algorithm achieved 84.7% accuracy in predicting stakeholder satisfaction levels, significantly outperforming Decision Trees (76.3%), Support Vector Machines (78.1%), and Logistic Regression (72.8%). Feature importance analysis revealed practical equipment adequacy (0.28), instructor technical expertise (0.23), and hands-on training sufficiency (0.19) as the most critical quality factors. Predictive modeling for 2025-2028 demonstrated that faculty training programs will achieve the highest improvement effectiveness (50% satisfaction increase), while algorithm-determined sequential implementation strategies will achieve 89% stakeholder satisfaction compared to 67% for conventional approaches. The analysis identified faculty training enhancement as the most critical improvement priority for 73% of institutions, providing evidence-based guidance for optimal resource allocation in remote driving technology vocational education programs.
Authors: Yuanfang Shi, Xiaojiao Wang, Lin Cheng
Language: English
Subfield: Education
Field: Social Sciences
Domain: Social Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W7114801875
