Choosing which universities to apply to as a graduate student can be a difficult task. The application process is constantly evolving, and it can be hard to know if your profile meets the requirements of a particular school. Additionally, the expense of submitting an application to a university is frequently substantial, so it is important to think carefully about your options based on your profile. One tool that can be helpful in this process is a university admission prediction system. These systems use data from previous applicants to various universities, including whether they were accepted or rejected, to estimate your chances of getting into a specific school. In the past, these prediction systems have had some limitations, such as not considering important factors like GRE scores or research experience, and not being very accurate. In our research, we suggest a new stacked ensemble model that can predict a student’s chances of being accepted to a particular university with a high level of accuracy. Our model considers several factors pertaining to the student, such as their research and industry experience. We also compare our system to other machine learning algorithms and find out if it outperforms all of them.