Indian Journal of Science and Technology
DOI: 10.17485/ijst/2018/v11i37/130842
Year: 2018, Volume: 11, Issue: 37, Pages: 1-6
Original Article
Rommel L. Verecio*
Information Technology & Computer Education Leyte Normal University Philippines; [email protected]
*Author for correspondence
Rommel L. Verecio,
Information Technology & Computer Education Leyte Normal University Philippines; [email protected]
Objectives: This study predicts the employability skills acquired by the BS Information Technology graduates of Leyte Normal University, Tacloban City. Work skills or employability skills were identified based on the Commission on Higher Education (CHED) Memorandum Order 53, series of 2006, which categorizes as personal, interpersonal, and technical understanding skills. Methods: Using data mining to predict employability skills of the graduates particularly on the J48 algorithm a C4.5 decision tree model. The 10-Folds Cross-validation and Receiving Operating Characteristics Curve (ROC) was deployed to create a model and test the result based on the attributes. The collected datasets of this study are from the graduates from S.Y. 2015-2016 to 2017-2018. There are 138 datasets with six variables (Systems Development, Research, Business Operations, Technical Support, Interpersonal Skills, and Remarks). Findings: Decision tree model and decision rule for classification were created. There were 85.50% correctly classified with an AUC weighted mean of 85.10%. Hence, classified students who possess Expert (82.8%), Advanced (95%), and Intermediate (57.10%) OJT performance. The model has high acceptability to predict that Business Operations is the most important attribute in the On-the-Job Training. Wherein, students are trained to be productive, responsible and cooperative and have the initiative to act. Application/Improvements: The result of this study can be a basis for policy measures for effective OJT program. Further, for more improvement of this paper and model, additional parameters should be considered to have more factors involved in predicting employability skills.
Keywords: Decision Tree, Employability Skills, Machine Learning, On-the-Job Training, J48 Algorithm, BSIT, LNU
Subscribe now for latest articles and news.