Determining the profiles of young people from Buenos Aires with a tendency to pursue Computer Science studies

Abstract

Data Mining is a discipline related to the development and application of techniques for the extraction of new and useful information from large amounts of available data. The goal of this paper is to use these techniques on data extracted from a poll in order to identify the pro les of the young people showing interest in pursuing undergraduate studies in the eld of computer science. The paper describes the process of identification of the most salient features for high school students in a wide age range. It also includes the data preprocessing stage, fundamental in the process, as it strongly influences the development of the model obtained. Finally, results and conclusions are presented, as well as future lines of work.