Open AccessCombining Data Mining Techniques to Analyse Factors Associated with Allocation of Socioeconomic Resources at IFMG
Author(s) -
Eduardo Cardoso Melo,
Elisa Tuler,
Leonardo Rocha
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/kdmile.2021.17465
Subject(s) - computer science , index (typography) , feature selection , socioeconomic status , set (abstract data type) , institution , workload , selection (genetic algorithm) , vulnerability (computing) , data mining , data science , machine learning , knowledge management , world wide web , political science , computer security , population , demography , sociology , law , programming language , operating system
The granting of socioeconomic assistance to students from Federal Education Institutions is one of the ways found to provide finantial support during their studies, focusing primarily on those who are more socially vulnerable. Institutions carry out selection processes to identify students with a profile of demand and appropriately distribute the grants according to the budget available for this purpose. This article applied Data Mining techniques to a set of information from students who applied to receive scholarships at IFMG - Campus Bambuí, seeking to identify the attributes associated with the distribution of benefits and analyzing the adequacy of the current indicator used by the institution to classify the level of social vulnerability of students. The proposed methodology involved combining different machine learning algorithms, such as data classification and feature selection techniques. In addition to identifying the degree of importance of each attribute in the constructed model, the differential of this article is to present well-founded suggestions for new attributes that could be able to improve the index used by the institution and, consequently, optimize the workload of those involved with the analysis of selective processes. The composition of the institution's index with five new attributes resulted in a gain of around 10% in rating performance.