Predicting Success of University Applicants Based on Subjects’ Preferences as an Extra Tool for Admission Considerations Predictive Analytics Approach
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10362/136699 |
Resumo: | Project Work presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business Intelligence |
id |
RCAP_93ef3710a29a82cd3fa7f32b8fba974f |
---|---|
oai_identifier_str |
oai:run.unl.pt:10362/136699 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Predicting Success of University Applicants Based on Subjects’ Preferences as an Extra Tool for Admission Considerations Predictive Analytics ApproachUniversity AdmissionPredictive ModelingStudent Performance PredictionStudent Performance IndicatorsProject Work presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business IntelligenceThis study uses a dataset of student performance indicators and psychological patterns associated with each individual to examine the prediction efficiency of psychological traits on academic results, more specifically grade point average (GPA). We propose building a classification machine learning model that predicts GPA performance, dividing the students into the top and bottom performers. Several features were used in the modelling, namely, student's previous performance, such as GPA, course progression (how close the student master is related to previous academic courses), and personality traits obtained by surveying 319 students and recent graduates with a quiz developed by Association Better Future based on the RIASEC model for type theory of personality. It is widely accepted that psychological characteristics can impact student churn and performance (Costa and McCrae, 1992). Furthermore, numerous papers have found that GPA can be predicted by multiple factors, including past performance, intelligence coefficient (IQ), demographic background, previous area of studies, but, to increase the model’s accuracy, psychological factors are recommended for future works (Abele and Spurk, 2009). Whilst past performance and, to a lesser extent, IQ are currently evaluated in university admissions, psychological traits are yet to have a place in selecting the best candidates. In this study we propose that, although IQ and past performance are good indicators of student performance, the predictive power of psychological traits, when combined with these classical indicators, increases the predictability accuracy of the machine learning model. With this in mind, we used the performance of past and current university students, measured in GPA, analysed it against the collected psychological indicators and developed multiple machine learning models to predict the student GPA based on the collected indicators. These were divided into 3 groups: psychological traits only, GPA and age only, and a combination of both. Four types of models were used: neural networks, Support Vector Machines (SVM), decision forests and decision trees. Decision forests, for the problem at hand, consistently outperformed neural networks, SVM and decision trees both in accuracy and Area Under the Curve (AUC), the curve being the Receiver Operating Characteristic (ROC). From the database with 176 entries, comparing the models created with the GPA and age-based dataset with the ones based on the full dataset that includes psychological variables, decision forests were the model with higher fitness to the training model, and with the higher AUC against the validation set, with values of 0.717 and 0.790, respectively. The models based on the full dataset, including psychological variables, consistently outperformed the models based solely on the classical GPA predicting metrics. We further propose and discuss that the model can be used as an extra indicator for the admission process.Henriques, Roberto André PereiraRUNMenezes, Simão Caridade2022-04-20T16:13:38Z2022-04-112022-04-11T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/136699TID:202994139enginfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:14:40Zoai:run.unl.pt:10362/136699Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:48:45.616732Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Predicting Success of University Applicants Based on Subjects’ Preferences as an Extra Tool for Admission Considerations Predictive Analytics Approach |
title |
Predicting Success of University Applicants Based on Subjects’ Preferences as an Extra Tool for Admission Considerations Predictive Analytics Approach |
spellingShingle |
Predicting Success of University Applicants Based on Subjects’ Preferences as an Extra Tool for Admission Considerations Predictive Analytics Approach Menezes, Simão Caridade University Admission Predictive Modeling Student Performance Prediction Student Performance Indicators |
title_short |
Predicting Success of University Applicants Based on Subjects’ Preferences as an Extra Tool for Admission Considerations Predictive Analytics Approach |
title_full |
Predicting Success of University Applicants Based on Subjects’ Preferences as an Extra Tool for Admission Considerations Predictive Analytics Approach |
title_fullStr |
Predicting Success of University Applicants Based on Subjects’ Preferences as an Extra Tool for Admission Considerations Predictive Analytics Approach |
title_full_unstemmed |
Predicting Success of University Applicants Based on Subjects’ Preferences as an Extra Tool for Admission Considerations Predictive Analytics Approach |
title_sort |
Predicting Success of University Applicants Based on Subjects’ Preferences as an Extra Tool for Admission Considerations Predictive Analytics Approach |
author |
Menezes, Simão Caridade |
author_facet |
Menezes, Simão Caridade |
author_role |
author |
dc.contributor.none.fl_str_mv |
Henriques, Roberto André Pereira RUN |
dc.contributor.author.fl_str_mv |
Menezes, Simão Caridade |
dc.subject.por.fl_str_mv |
University Admission Predictive Modeling Student Performance Prediction Student Performance Indicators |
topic |
University Admission Predictive Modeling Student Performance Prediction Student Performance Indicators |
description |
Project Work presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business Intelligence |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-04-20T16:13:38Z 2022-04-11 2022-04-11T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10362/136699 TID:202994139 |
url |
http://hdl.handle.net/10362/136699 |
identifier_str_mv |
TID:202994139 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799138088378695680 |