A Novel Self-Organizing Map (SOM) With Data Mining Model for Formulation of Vocational Education Policies

Abstract

Data mining is a process of extracting valuable and previously unknown patterns, insights, and knowledge from large datasets. data mining techniques enable the analysis of educational data to inform multi-level vocational education policies that contribute to regional sustainable development. By leveraging the power of data, policymakers can make evidence-based decisions, align vocational education with regional needs, and enhance the effectiveness and relevance of vocational education programs in promoting sustainable development. In this paper proposed an Associative Rule Kohonen SOM (AR-KS) for multi-level vocational educational policies assessment for sustainable development. Initially, the proposed AR-KS model collects relevant data, including information on vocational education programs, student performance records, regional development indicators, and policy documents. This data is then preprocessed to ensure consistency and quality. The next step involves training a Kohonen SOM using the preprocessed data. The SOM forms a topological map where each neuron represents a unique combination of policy variables and regional development factors. This map captures the multidimensional relationships among the variables and provides a visual representation of the policy space. The relationship between the patterns is computed with the associative rule-based training of SOM between variables. The analysis of the AR-KS framework allows policymakers to assess the impact of different vocational education policies on sustainable development goals. Overall, the proposed AR-KS framework offers a novel approach for assessing multi-level vocational educational policies in the context of sustainable development.