Deep Learning in Predicting High School Grades: A Quantum Space of Representation
This paper applies deep learning to the prediction of Portuguese high school grades. A deep multilayer perceptron and a multiple linear regression implementation are undertaken. The objective is to demonstrate the adequacy of deep learning as a quantitative explanatory paradigm when compared with th...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ital Publication
2022-09-01
|
| Series: | Emerging Science Journal |
| Subjects: | |
| Online Access: | https://ijournalse.org/index.php/ESJ/article/view/1288 |
| _version_ | 1828068059711012864 |
|---|---|
| author | Ricardo Costa-Mendes Frederico Cruz-Jesus Tiago Oliveira Mauro Castelli |
| author_facet | Ricardo Costa-Mendes Frederico Cruz-Jesus Tiago Oliveira Mauro Castelli |
| author_sort | Ricardo Costa-Mendes |
| collection | DOAJ |
| description | This paper applies deep learning to the prediction of Portuguese high school grades. A deep multilayer perceptron and a multiple linear regression implementation are undertaken. The objective is to demonstrate the adequacy of deep learning as a quantitative explanatory paradigm when compared with the classical econometrics approach. The results encompass point predictions, prediction intervals, variable gradients, and the impact of an increase in the class size on grades. Deep learning’s generalization error is lower in the student grade prediction, and its prediction intervals are more accurate. The deep multilayer perceptron gradient empirical distributions largely align with the regression coefficient estimates, indicating a satisfactory regression fit. Based on gradient discrepancies, a student’s mother being an employer does not seem to be a positive factor. A benign paradigm shift concerning the balance between home and career affairs for both genders should be reinforced. The deep multilayer perceptron broadens the spectrum of possibilities, providing a quantum solution hinged on a universal approximator. In the case of an academic achievement-critical factor such as class size, where the literature is neither unanimous on its importance nor its direction, the multilayer perceptron formed three distinct clusters per the individual gradient signals.
Doi: 10.28991/ESJ-2022-SIED-012
Full Text: PDF |
| first_indexed | 2024-04-10T23:56:59Z |
| format | Article |
| id | doaj.art-a1b137b032a64029bdcfe7b552f0a75d |
| institution | Directory Open Access Journal |
| issn | 2610-9182 |
| language | English |
| last_indexed | 2024-04-10T23:56:59Z |
| publishDate | 2022-09-01 |
| publisher | Ital Publication |
| record_format | Article |
| series | Emerging Science Journal |
| spelling | doaj.art-a1b137b032a64029bdcfe7b552f0a75d2023-01-10T12:50:26ZengItal PublicationEmerging Science Journal2610-91822022-09-016016618710.28991/ESJ-2022-SIED-012375Deep Learning in Predicting High School Grades: A Quantum Space of RepresentationRicardo Costa-Mendes0Frederico Cruz-Jesus1Tiago Oliveira2Mauro Castelli3NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de Campolide, 1070-312 Lisboa,NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de Campolide, 1070-312 Lisboa,NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de Campolide, 1070-312 Lisboa,NOVA Information Management School (NOVA IMS), Universidade Nova de Lisboa, Campus de Campolide, 1070-312 Lisboa,This paper applies deep learning to the prediction of Portuguese high school grades. A deep multilayer perceptron and a multiple linear regression implementation are undertaken. The objective is to demonstrate the adequacy of deep learning as a quantitative explanatory paradigm when compared with the classical econometrics approach. The results encompass point predictions, prediction intervals, variable gradients, and the impact of an increase in the class size on grades. Deep learning’s generalization error is lower in the student grade prediction, and its prediction intervals are more accurate. The deep multilayer perceptron gradient empirical distributions largely align with the regression coefficient estimates, indicating a satisfactory regression fit. Based on gradient discrepancies, a student’s mother being an employer does not seem to be a positive factor. A benign paradigm shift concerning the balance between home and career affairs for both genders should be reinforced. The deep multilayer perceptron broadens the spectrum of possibilities, providing a quantum solution hinged on a universal approximator. In the case of an academic achievement-critical factor such as class size, where the literature is neither unanimous on its importance nor its direction, the multilayer perceptron formed three distinct clusters per the individual gradient signals. Doi: 10.28991/ESJ-2022-SIED-012 Full Text: PDFhttps://ijournalse.org/index.php/ESJ/article/view/1288data science applications in educationsecondary educationsocial sciencesdeep learningartificial neural networksacademic achievement. |
| spellingShingle | Ricardo Costa-Mendes Frederico Cruz-Jesus Tiago Oliveira Mauro Castelli Deep Learning in Predicting High School Grades: A Quantum Space of Representation Emerging Science Journal data science applications in education secondary education social sciences deep learning artificial neural networks academic achievement. |
| title | Deep Learning in Predicting High School Grades: A Quantum Space of Representation |
| title_full | Deep Learning in Predicting High School Grades: A Quantum Space of Representation |
| title_fullStr | Deep Learning in Predicting High School Grades: A Quantum Space of Representation |
| title_full_unstemmed | Deep Learning in Predicting High School Grades: A Quantum Space of Representation |
| title_short | Deep Learning in Predicting High School Grades: A Quantum Space of Representation |
| title_sort | deep learning in predicting high school grades a quantum space of representation |
| topic | data science applications in education secondary education social sciences deep learning artificial neural networks academic achievement. |
| url | https://ijournalse.org/index.php/ESJ/article/view/1288 |
| work_keys_str_mv | AT ricardocostamendes deeplearninginpredictinghighschoolgradesaquantumspaceofrepresentation AT fredericocruzjesus deeplearninginpredictinghighschoolgradesaquantumspaceofrepresentation AT tiagooliveira deeplearninginpredictinghighschoolgradesaquantumspaceofrepresentation AT maurocastelli deeplearninginpredictinghighschoolgradesaquantumspaceofrepresentation |