SUMMARY
Opening job vacancies using the Internet will receive many applications quickly. Manually filtering resumes takes a lot of time and incurs huge costs. In addition, this manual screening process tends to be inaccurate due to fatigue conditions and fails in obtaining the right candidate for the job. This paper proposed a solution to automatically generate the most suitable candidate from the application document. In this study, 126 application documents from a private company were used for the experiment. The documents consist of 41 documents for Human Resource and Development (HRD) staff, 42 documents for IT (Data Developer), and 43 documents for the Marketing position. Text Processing is implemented to extract relevant information such as skills, education, experiences from the unstructured resumes and summarize each application. A specific dictionary for each vacancy is generated based on terms used in each profession. Two methods are implemented and compared to match and score the application document, namely Document Vector and N-gram analysis. The highest the score obtained by one document, the highest the possibility of application to be accepted. The two methods’ results are then validated by the real selection process by the company. The highest accuracy was achieved by the N-Gram method in IT vacancy with 87,5%, while the Document Vector showed 75% accuracy. For Marketing staff vacancy, both methods achieved the same accuracy as 78%. In HRD staff vacancy, the N-Gram method showed 68%, while Document Vector showed 74%. In conclusion, overall the N-gram method showed slightly better accuracy compared to the Document Vector method.