A hybrid model combining environmental analysis and machine learning for predicting AI education quality

Area of Science:

• Educational Technology
• Artificial Intelligence
• Management Science

Background:

• Increasing need for artificial intelligence (AI) tools in university management systems.
• Rapid development of AI-based platforms for educational institutions.

Purpose of the Study:

• Propose corrective measures for AI education within university teaching and learning management.
• Introduce a novel approach for evaluating the quality of AI training programs in higher education.

Main Methods:

• Macro environment analysis (external, intermediate, internal) for corrective measures.
• Development of a multilayer perceptron (MLP) algorithm for quality evaluation.
• Utilizing Capuchin Search Algorithm (CapSA) for neural network weight adjustment.

Main Results:

• The proposed AI model demonstrated high accuracy in predicting education quality (CCC: 0.9611, SROCC: 0.9805, PLCC: 0.9731, R²: 0.9803).
• Corrective measures across all environmental factors positively impact AI education development in universities.
• The proposed approach outperformed other models in evaluating AI training programs.

Conclusions:

• The proposed AI-driven approach effectively evaluates AI training program quality in higher education.
• Strategic implementation of corrective measures is crucial for advancing AI education in universities.
• AI integration enhances university management and educational outcomes.