Prediction of Student Entrepreneurship Future Work based on Entrepreneurship Course using the Naïve Bayes Classifier Model

Abstract

Entrepreneurs are critical to a country's economic progress and job creation. Few people felt schools have much to offer with business a generation ago. Students are expected to be an entrepreneur as the outcome of the course. The goal of this study is building a model to predict students' future employment, particularly in the field of entrepreneurship, using big data analysis and data mining. Various educational institutions can use data mining methodologies to identify hidden patterns in data contained in databases. The feature selection technique was utilised in this study to select and assess the significance of each element. The model was built using the final parameters determined by the feature selection technique (Correlation Based Feature Selection). Using the 10-fold cross validations for training and testing dataset distribution, the Naïve Bayes classifier was used to forecast the students' future of work. The dataset for the study was gathered from a student's performance report at Universitas Negeri Medan's engineering department. The effectiveness of using feature selection algorithms was compared to the effectiveness of not using feature selection algorithms, and the results are discussed. According to the findings of this study, the accuracy of Naïve Bayes with Correlation Based Feature Selection is 87.4%, which is higher than the model that did not use any feature selection. It was also discovered that the overall accuracy of the Correlation Based Feature Selection and Naïve Bayes Classifier models appears to be higher than that of the other treatments.