Integration of Fuzzy Multi-Attribute Decision Making and Clustering Methods for Student Apprenticeship Recommendations

Abstract

Harmonious vocational education and training with the company, industry, and occupation are carried out by providing access to apprenticeships and industrial work practices. This study proposes a method of clustering student competencies in vocational education and training institutions as a recommendation for students who can be apprenticed to the company, industry, and occupation. The Fuzzy Multi-Attribute Decision Making (FMADM) approach is proposed with a combination of two methods, namely Fuzzy Simple Additive Weighting and Fuzzy Technique for Order Preference by Similarity to Ideal Solution (FSAW-TOPSIS). FSAW-TOPSIS provides a more optimal solution and better performance. The FSAW-TOPSIS method which is integrated with clustering produces an accuracy of 100% for the Decision Tree method, with a Neural Network with the best accuracy marked by the smallest RMSE value of 0.246. FSAW-TOPSIS integration and clustering provide optimal student apprenticeship recommendations as material for decision-making for leaders of vocational education and training institutions to apprentice their students in the company, industry, and occupation.