Profiling of students and alumni is a study that aims to identify the characteristics of individuals who enter and leave an educational institution. Through the analysis of the collected data, this study can provide valuable information for the institution namely the University of Logistics and International Business to improve the programs offered and help students and alumni to plan their careers. The data used in this study were obtained from scraping on the linkedin web, which totaled 300 data. With the ratio of the distribution of testing data and test data as much as 75%: 25%. The purpose of this research is to apply the decision tree method to student and alumni profiling at the International Logistics and Business University to see how accurate the profiling is produced using the id3 decision tree method. Conclusions that can be drawn from the results and discussion of the research that has been done. So the most influential attributes for getting students and alumni to get jobs are organization and certification skills. After forming a decision tree rule with the id3 algorithm, pre-pruning and post-pruning is done to ensure that the resulting decision tree is not overfitting. Then the accuracy obtained for the train data is 0.64 or 64% and the test data is 0.61 or 61%. With a recall of 0.36 or 36% and a precision of 0.6 or 60%.
Copyrights © 2023