Clustering of Municipalities in Rhineland-Palatinate Using Publicly Available Data
School Name
South Carolina Governor's School for Science and Mathematics
Grade Level
12th Grade
Presentation Topic
Computer Science
Presentation Type
Mentored
Abstract
In the study of population theory, municipalities and their characteristics hold substantial value. My group and I categorized municipalities in our region of Germany using Artificial Intelligence. During this process, we attempted to extract meaningful data about the correlation between municipalities. To accomplish this, we tested different data clustering algorithms to group the municipalities together. Once we grouped our data points together, we used an experimental calculation called the Silhouette Score. By using this score, we were indeed able to create meaningful clusters. We noticed that our clustering algorithms best organized municipalities into two groups. Due to this success, we learned that the Silhouette Score is a formula that has large potential to be adopted in the realm of data science as common practice. Therefore, while our study was able to cluster together municipalities in the Rhineland-Palatinate region of Germany, we also uncovered the usefulness of a mathematical calculation in the realm of data science.
Recommended Citation
Mathisz, Albert, "Clustering of Municipalities in Rhineland-Palatinate Using Publicly Available Data" (2026). South Carolina Junior Academy of Science. 41.
https://scholarexchange.furman.edu/scjas/2026/all/41
Location
Furman Hall 204
Start Date
3-28-2026 10:45 AM
Presentation Format
Oral Only
Group Project
No
Clustering of Municipalities in Rhineland-Palatinate Using Publicly Available Data
Furman Hall 204
In the study of population theory, municipalities and their characteristics hold substantial value. My group and I categorized municipalities in our region of Germany using Artificial Intelligence. During this process, we attempted to extract meaningful data about the correlation between municipalities. To accomplish this, we tested different data clustering algorithms to group the municipalities together. Once we grouped our data points together, we used an experimental calculation called the Silhouette Score. By using this score, we were indeed able to create meaningful clusters. We noticed that our clustering algorithms best organized municipalities into two groups. Due to this success, we learned that the Silhouette Score is a formula that has large potential to be adopted in the realm of data science as common practice. Therefore, while our study was able to cluster together municipalities in the Rhineland-Palatinate region of Germany, we also uncovered the usefulness of a mathematical calculation in the realm of data science.
