Many people look to get into a "top-ranked" university, whether if it's for work, undergraduate, graduate, or just to build their network and resume. Those who want to travel overseas to study at a prestigious university often look at world rankings to decided whether or not to apply. Over the next few years, more and more students will apply to top universities. However, some prospective students may want to identify universities that have been on the rise in world rankings, and may continue this rise.
Quacquarelli Symonds, or QS World University Rankings have been ranking top universities around the world for decades. On multiple sites, there is a consensus that the rankings are reliable, considering factors like reputation, research, student-faculty ratio, and more. The goal of this project is to help prospective students compare top universities, cities and countries with top universities, and trends over the last few years to predict next year's university rankings.
This predictor may not only help students find universities on the rise over the last few years, but it can also help university staff identify if their university's ranking has increased or decreased over the last few years. This predictor can also help international students find cities or countries with top well-known universities. One negative outcome of this classifier is that it may decrease self-confidence of those already studying at universities that have decreased in their QS rankings.
The dataset we will use is the QS World ranked Universities (2018-2022) to observe the following features for each university:
| Year | Rank | Name | Point | City | Country |
|---|---|---|---|---|---|
| 2018 | 1 | Harvard University | 97.7 | Cambridge | United States |
| 2018 | 2 | University of Cambridge | 94.6 | Cambridge | United Kingdom |
| 2018 | 2 | University of Oxford | 94.6 | Oxford | United Kingdom |
| 2018 | 4 | Massachusetts Institute of Technology (MIT) | 92.5 | Cambridge | United States |
| 2018 | 5 | Johns Hopkins University | 92.1 | Baltimore | United States |
The points used to calculate their "score" come from a variety of factors.
The dataset alone is quite subjective to whoever made the list and the criteria for a good score. There are a variety of factors that can make a university excellent, and each applicant's personal choice depends on their concentration, financial situation, location, and more. Additionally, the data has not been updated for months, so by the time this project is finished, our classifier may be slightly outdated. Finally, as we can see from the first two lines of our data, under the "City" column we have two cities that have the same name, "Cambridge." This may require further data analysis to differentiate between two cities with the same name.
We will use a regression line for each university, and have many subplots for at least the first 200 universities. We seek to estimate the ranking by "points" in 2023 of each university, which will help us find which universities have increased in rankings over the last few years. To compare location, we will use simple data visualization to show the most popular cities and countries with top universities.