On Data Protection Regulations, Big Data and Sledgehammers in Higher Education
Universities in Latin America commonly gather much more information about their students than allowed by data protection regulations in other parts of the world. We have tackled the question of whether abundant socio-economic data can be harnessed for the purpose of predicting academic outcomes and,...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/15/3084 |
| _version_ | 1819083528748400640 |
|---|---|
| author | Roberto Agustín García-Vélez Martín López-Nores Gabriel González-Fernández Vladimir Espartaco Robles-Bykbaev Manolis Wallace José J. Pazos-Arias Alberto Gil-Solla |
| author_facet | Roberto Agustín García-Vélez Martín López-Nores Gabriel González-Fernández Vladimir Espartaco Robles-Bykbaev Manolis Wallace José J. Pazos-Arias Alberto Gil-Solla |
| author_sort | Roberto Agustín García-Vélez |
| collection | DOAJ |
| description | Universities in Latin America commonly gather much more information about their students than allowed by data protection regulations in other parts of the world. We have tackled the question of whether abundant socio-economic data can be harnessed for the purpose of predicting academic outcomes and, thereby, taking proactive actions in student attention, course planning and resource management. A study was conducted to analyze the data gathered by a private university in Ecuador over more than 20 years, to normalize them and to parameterize a Multi-Layer Perceptron neural network, whose best-performing configuration would be used as a benchmark for the comparison of more recent and sophisticated Artificial Intelligence techniques. However, an extensive scan of hyperparameters for the perceptron—exploring more than 12,000 configurations—revealed no significant relationships between the input variables and the chosen metrics, suggesting that there is no gain from processing the extensive socio-economic data. This finding contradicts the expectations raised by previous works in the related literature and in some cases highlights important methodological flaws. |
| first_indexed | 2024-12-21T20:34:00Z |
| format | Article |
| id | doaj.art-868f3b0df16042aa9f5440a972a5f697 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-21T20:34:00Z |
| publishDate | 2019-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-868f3b0df16042aa9f5440a972a5f6972022-12-21T18:51:09ZengMDPI AGApplied Sciences2076-34172019-07-01915308410.3390/app9153084app9153084On Data Protection Regulations, Big Data and Sledgehammers in Higher EducationRoberto Agustín García-Vélez0Martín López-Nores1Gabriel González-Fernández2Vladimir Espartaco Robles-Bykbaev3Manolis Wallace4José J. Pazos-Arias5Alberto Gil-Solla6Research Group of Artificial Intelligence and Assistance Technology (GIIATA), Universidad Politécnica Salesiana, Cuenca 010102, EcuadorAtlantTIC Research Center, Department of Telematics Engineering, University of Vigo, 36310 Vigo, SpainDeicom Technologies S.L., 36203 Vigo, SpainResearch Group of Artificial Intelligence and Assistance Technology (GIIATA), Universidad Politécnica Salesiana, Cuenca 010102, EcuadorΓAB LAB—Knowledge and Uncertainty Research Laboratory, Department of Informatics and Telecommunications, University of Peloponnese, 22100 Tripoli, GreeceAtlantTIC Research Center, Department of Telematics Engineering, University of Vigo, 36310 Vigo, SpainAtlantTIC Research Center, Department of Telematics Engineering, University of Vigo, 36310 Vigo, SpainUniversities in Latin America commonly gather much more information about their students than allowed by data protection regulations in other parts of the world. We have tackled the question of whether abundant socio-economic data can be harnessed for the purpose of predicting academic outcomes and, thereby, taking proactive actions in student attention, course planning and resource management. A study was conducted to analyze the data gathered by a private university in Ecuador over more than 20 years, to normalize them and to parameterize a Multi-Layer Perceptron neural network, whose best-performing configuration would be used as a benchmark for the comparison of more recent and sophisticated Artificial Intelligence techniques. However, an extensive scan of hyperparameters for the perceptron—exploring more than 12,000 configurations—revealed no significant relationships between the input variables and the chosen metrics, suggesting that there is no gain from processing the extensive socio-economic data. This finding contradicts the expectations raised by previous works in the related literature and in some cases highlights important methodological flaws.https://www.mdpi.com/2076-3417/9/15/3084data protectionstudent recordsperformance predictionMulti-Layer Perceptrondeep learning |
| spellingShingle | Roberto Agustín García-Vélez Martín López-Nores Gabriel González-Fernández Vladimir Espartaco Robles-Bykbaev Manolis Wallace José J. Pazos-Arias Alberto Gil-Solla On Data Protection Regulations, Big Data and Sledgehammers in Higher Education Applied Sciences data protection student records performance prediction Multi-Layer Perceptron deep learning |
| title | On Data Protection Regulations, Big Data and Sledgehammers in Higher Education |
| title_full | On Data Protection Regulations, Big Data and Sledgehammers in Higher Education |
| title_fullStr | On Data Protection Regulations, Big Data and Sledgehammers in Higher Education |
| title_full_unstemmed | On Data Protection Regulations, Big Data and Sledgehammers in Higher Education |
| title_short | On Data Protection Regulations, Big Data and Sledgehammers in Higher Education |
| title_sort | on data protection regulations big data and sledgehammers in higher education |
| topic | data protection student records performance prediction Multi-Layer Perceptron deep learning |
| url | https://www.mdpi.com/2076-3417/9/15/3084 |
| work_keys_str_mv | AT robertoagustingarciavelez ondataprotectionregulationsbigdataandsledgehammersinhighereducation AT martinlopeznores ondataprotectionregulationsbigdataandsledgehammersinhighereducation AT gabrielgonzalezfernandez ondataprotectionregulationsbigdataandsledgehammersinhighereducation AT vladimirespartacoroblesbykbaev ondataprotectionregulationsbigdataandsledgehammersinhighereducation AT manoliswallace ondataprotectionregulationsbigdataandsledgehammersinhighereducation AT josejpazosarias ondataprotectionregulationsbigdataandsledgehammersinhighereducation AT albertogilsolla ondataprotectionregulationsbigdataandsledgehammersinhighereducation |