Multi-Attribute Clustering of Student's Entrepreneurial Potential Mapping Based on Its Characteristics and the Affecting Factors

Abstract

Indonesian government's efforts to improve the growth of scientific-based young entrepreneurs from universities require the support of information in the form of entrepreneurial potential students. The clustering of entrepreneurial potential aims to classify student data based on their diverse characteristic. However, the problem is that the entrepreneurial potential of students is affected by many factors, where each factor has varied characteristics, both in terms of its value and weight. Regarding these affecting factors, Simple Multi-Attribute Rating Technique (SMART) is proposed as a solution to simplify the assessment of entrepreneurial potential per criteria. Therefore, the clustering process to the dataset has the concept of multi clustering attribute. The experimental results show that the multi-attribute clustering with the K-Means algorithm has better performance than normal clustering. It can decrease the value of Sum of Squared Errors (SSE) significantly by 90% and reduce the number of iterations by 30% so that the time in building model reduce by 1% and decrease the value of Incorrectly Cluster Instance (ICI) by 3%. Based on visualization, multi-attribute clustering results are also easier to interpret.