Analysis on Behavioral Patterns of to enhance career test John Holland theory by using Data Mining Technique

Abstract

The objective of this research was to analysis to enhance career test inventory based-on John Holland theory by using Data Mining Technique. The surveyed questionnaire was used with 3,000 students at Chamnong Business Administration Technological College. The data of graduates consisted of Sex Age Branch GPA Educational goals Domicile Parenting career and The average income of the family. This research used and compared the results of Decision Tree J48, Logistic Model Trees (LMT), Random Forest (RF), Naïve Bayes and Artificial Neural Network were used to build the prediction models. Moreover,
10-fold cross validation utilized to split the data into the training and test set. This research has measured performance models with accuracy precision Recall and F-measure. Experimental result demonstrated that Random Forest superior to C4.5 LMT Naïve Bayes and Artificial Neural Network with accuracy 91.37%, precision 91.30% Recall 91.40% and F-measure 91.30%. The results in this experiment can be applied to the relevant authorities to development plans course structure or education plan.