<![CDATA[Extensive use of alumni data by evaluating alumni competency levels, such as in the world of education, human resources, or university rankings. Therefore, the use of powerful algorithms such as SVM and easy-to-use interfaces such as Streamlit can provide great benefits in various contexts. How to measure the performance of the SVM model in assessing alumni competency levels, and how to interpret the evaluation results correctly for users is the main focus of this research. One way of searching for alumni is to assess the competitiveness of graduates and collect relevant assessment information from universities. This research is a continuation of the analysis of alumni competency levels using the SVM algorithm method which was implemented using the Streamlit application to determine (alumni's) perceptions of skill proficiency and the level of skills demanded by the world of work. The data used results from the UNISKA Tracer 2021 questionnaire responses to questions of 30 competencies from 3,117 respondents. The results of the implementation created will display the results of the classification with the information Competent and Not Competent by entering the values of 30 variables in the Tracer Study results. If the competency is in alumni, we know that companies can also support personal development through training or certain training courses. One way to assess a student's skill level in machine learning is to use a dataset as training data so that benchmarking can be carried out using accurate classification methods.]]>
Copyrights © 2023
