Data Mining And Modeling Of Time-Evolving Graphs

As our access to more and more data continues to increase with the world’s advancements, so does the difficulty on how to properly store and analyze it for useful results. Due to the nature of many of today’s datasets that are vast in size and contain such complexities as time-evolving elements, traditional methods of data storage and analysis are often not suitable for application. Therefore, the process of data mining and modeling of time-evolving graphs was developed in order to effectively store and analyze such datasets that would have otherwise been inaccessible. In particular, my research project this summer focused on performing the operations of data mining and modeling of time evolving graphs on a dataset that was built up of countries and their values of international trading. Since the practice of modeling time-evolving graphs is still fairly new, the main goal of this project was to provide additional time-evolving graphs to the limited supply for other scientists in this area of research to study. Additionally, my mentor and I wanted to perform basic data mining processes on the graph in order to study the possible relationships between a country’s trading patterns and its other attributes. Although simply constructing the time-evolving graph left little time in the summer project for the data analysis process of data mining to be performed, it is likely that further data mining will be practiced and performed on our time-evolving graph in the future.