Adaptive Machine Learning-Based Personalized Sustainability Learning for Improving Student Understanding and Behavioral Change

Sustainability education establishes a better understanding for students who study sustainability, yet fails to create observable changes in student conduct. This study presents an adaptive machine learning-based educational framework that predicts student sustainability topic comprehension and provides customized learning resources to enhance academic performance and environmental sustainability practices. A synthetic dataset of 9600 records and 21 attributes was generated to simulate student interaction with eight sustainability topics, including climate change, carbon footprint, recycling, water conservation, renewable energy, sustainable transport, food waste, and green buildings. The dataset contained student demographic information, together with their academic performance indicators, their participation metrics, their quiz results, and their conduct assessment scores, which were collected before and after their educational process. The Random Forest classifier was developed to forecast three different levels of comprehension, which included low comprehension, medium comprehension, and high comprehension. The model achieved an accuracy of 0.999, precision of 0.999, recall of 0.999, and F1-score of 0.9989. Students in the adaptive group increased their quiz scores by an average of 15.21 points while students in the control group improved their scores by 6.08 points. The adaptive group showed a mean behavior change of 12.02 points while the control group displayed a 3.54-point change. The greatest improvements occurred among students who began with limited knowledge because the adaptive group attained 17.93 points in quiz improvement and 13.80 points in behavior change. The results demonstrate that the adaptive learning framework successfully simulates personalized sustainability education paths that proceed through controlled testing environments. The synthetic dataset testing showed that the framework created distinct learning patterns, which proved that academic performance and sustainability behavior enhancements showed better results than the fixed learning method. The findings demonstrate proof-of-concept results that show that adaptive machine learning can be successfully integrated into sustainability education, but they do not demonstrate actual educational effectiveness in real-world settings.