<![CDATA[This study analyzes the influence of artificial intelligence (AI) based recommendation systems on the satisfaction of vocational students, focusing on two main variables: feature mapping and technological readiness. The research background is driven by the need for more adaptive and personalized learning, considering that conventional methods tend to be generic and overlook individual differences. Involving 183 vocational students selected through purposive sampling, the study employs a quantitative approach with descriptive and associative methods. Data were collected using valid and reliable questionnaires with a 1–5 Likert scale and analyzed using multiple linear regression. The results indicate that both feature mapping and technological readiness have a positive and significant influence on student satisfaction. Simultaneously, these two variables explain 43% of the variation in student satisfaction. Partially, feature mapping has the most dominant influence compared to technological readiness, indicating the importance of adaptive feature design in AI-based recommendation systems. This study proves that technology-based learning material personalization if supported by adequate infrastructure can enhance the learning experience and satisfaction of vocational students. Therefore, the study recommends the development of AI-based adaptive learning models that prioritize aspects of feature design and technological readiness to improve the effectiveness and quality of vocational education.]]>
Copyrights © 2025
