<![CDATA[Problems with applications are potentially to disrupt business operational processes, especially in companies that depend entirely on applications. Therefore, speed and accuracy in handling every application problem that occurs is needed. One way to deal with various application problems effectively is to look for similar issues that have occurred before, and then take the handling solution as a reference for handling the current issue. This research aims to develop a recommendation system for handling application problems that can help the performance of the support services team. This system uses a cosine similarity algorithm with Term Frequency-Inverse Document Frequency weighting to find similar constraints based on the description. Before processing, the constraint description is summarized first using Gemini AI. Solutions to the obstacles found are used as a reference for handling current obstacles. The result of this research is that the system can summarize descriptions of issues and search for similar issues based on the dataset that has been trained. The recommendation system for handling application problems was well received by users, as evidenced by a score of 93.1% from 30 respondents who filled out the User Acceptance Test questionnaire.]]>
Copyrights © 2025
