PREDICTOR USED FOR PERSONNEL SELECTION BASED ON CURRICULUM VITAE

• Main Author: Chandra - NIM : 13514034 , Evita
• Format: Theses
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/27021
• Institution: Institut Teknologi Bandung

This research was conducted to develop a machine learning model that can predict personnel selection results based on Curriculum Vitae information. In Indonesia, personnel selections are done manual by Human Resource Development Staff. This thing may caused personnel selection can take a long time to be processed and poor judgments by the Human Resource Development Staff. To solve those problems, In this final project, the prediction machine learning model were made by comparing three kinds of machine learning algorithm, Knearest neighbor (KNN), support vector machine (SVM), and random forest. Some features and parameters were also configured to test the effects of feature selection and parameter tuning to the model’s performances. After the experiments and testing was conducted, the final results show that the best algorithm among the three algorithm that were used is Random Forest with some parameters configured, such as estimator value changed to 85, maximum depth changed to 10, features maximum changed to 7.This model achived a good performance with 77% accuracy score, 79% precision score, 78% recall score, and 78% F1 Score.