Model Klasifikasi Machine Learning untuk Prediksi Ketepatan Penempatan Karir

Abstract

The complexity of the job market requires individuals and organizations to understand the trends and needs of the world of work. One of the main challenges is the right career placement. That is becoming increasingly popular is the use of Machine Learning algorithms in the decision-making process. ML classification models such as Random Forest, Decision Tree, Naïve Bayes, KNN, and SVM have demonstrated their potential in uncovering hidden patterns from data, including a person's educational history, work experience and interests. In this research, the application of the ML classification model is aimed at predicting career placement. From the data sample used of 215, this research evaluates the effectiveness of various ML models in the context of career placement. As a result, the Random Forest Model is superior to other proposed models with an accuracy value of 87% and an AUC/ROC value of 0.93 which indicates a very good classification value. Meanwhile, the SVM model with Linear Kernel shows the lowest performance with an accuracy value of 67%. Apart from getting information on the best accuracy and AUC/ROC values, the results of this research found that the 'ssc_presentage' attribute (high school exam percentage) is an important factor in career placement decisions.