<![CDATA[This study aims to present an artificial intelligence-based framework that combines learning analytics with operational optimization, which can address the ever-present problems concerning technology and vocational education. In the case of vocational institutions, it has been noticed that while learning environments are increasingly embracing the incorporation of digital technologies, the connection between the use of data for educational outcomes and operational decision-making remains disconnected. In many instances, learning-related data is analyzed separately from production-oriented activities, which include scheduling, resource allocation, and process efficiency, despite the fact that these activities are part of the learning process in the factory and learning environments. This study aims to address the disconnect between the use of learning-related data and production-oriented activities through the incorporation of perspectives from industrial engineering and informatics, which are integrated into a single framework that is oriented towards artificial intelligence. Machine learning is utilized for the representation of learning processes, while optimization techniques are used for decision-making regarding task allocation, scheduling, and resource allocation. Instead of being restricted to a particular application domain, the framework is developed with the idea of adaptability so that it can be used across different contexts of vocational education. An empirical study was conducted within a particular context of a technology-oriented vocational education domain to assess the viability of the proposed framework. It was found that the integration of learning analytics with operational optimization provides a more consistent outcome compared to the individual analysis of these factors. It was also found that the proposed AI-based framework provides a better outcome for the assessment of competency as well as the prediction of performance, which leads to the efficiency of managing a production-oriented learning process. Such findings indicate the ability of the application of AI to support the field of vocational education more comprehensively. This study contributes to the field of research by proposing an interdisciplinary framework that goes beyond the idea of individual technological tools to offer a more comprehensive perspective on the adoption of AI within the context of vocational education.]]>
