Predictive Analysis of Graduate Students' Employability Using Machine Learning Techniques

Machine Learning evaluates datasets, finds patterns, and makes judgments based on data, it is essential for tackling a wide range of problems across multiple areas. The main objective of this study is to know, understand and analyze undergraduate student's employability status in Kombolcha Institute of Technology Wollo University. We prepared and cleaned the collected data to develop the predictive models. We used Random Forest and Gradient Boost ensemble Machine Learning methods. In order to explain the results of the experiment that classified students who are employed and unemployed. The study used different metrics to measure the performance of the developed model. Random Forest model accuracy is 96.7% and Gradient Boost model accuracy is 91.4%. Random Forest algorithm was discovered to perform better than other models.