Deep learning approach for predicting university dropout: a case study at Roma Tre University
Based on current trends in graduation rates, 39% of todays young adults on average across OECD countries are expected to complete tertiary-type A (university level) education during their lifetime. In 2017, an average of 10.6% of young people in the EU-28 were early leavers from education and traini...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Italian e-Learning Association
2020-05-01
|
| Series: | Je-LKS: Journal of E-Learning and Knowledge Society |
| Subjects: | |
| Online Access: | http://www.je-lks.org/ojs/index.php/Je-LKS_EN/article/view/1135192 |
| _version_ | 1811316711787331584 |
|---|---|
| author | Francesco Agrusti Mauro Mezzini Gianmarco Bonavolontà |
| author_facet | Francesco Agrusti Mauro Mezzini Gianmarco Bonavolontà |
| author_sort | Francesco Agrusti |
| collection | DOAJ |
| description | Based on current trends in graduation rates, 39% of todays young adults on average across OECD countries are expected to complete tertiary-type A (university level) education during their lifetime. In 2017, an average of 10.6% of young people in the EU-28 were early leavers from education and training. Therefore the level of dropout in the scenery of European education is one of the major issue to be faced in a near future. The main aim of the research is to predict, as early as possible, which student will dropout in the Higher Education context. The accurate knowledge of this information would allow one to effectively carry out targeted actions in order to limit the incidence of the phenomenon. The recent breakthrough on Neural Networks with the use of Convolutional Neural Networks architectures has become disruptive in AI. By stacking together tens or hundreds of convolutional neural layers, a “deep” network structure is obtained, which has been proved very effective in producing high accuracy models. In this research the administrative data of about 6000 students enrolled from 2009 in the Department of Education at Roma Tre University had been used to train a Convolutional Neural Network based. Then, the trained network provides a predictive model that predicts whether the student will dropout. Furthermore, we compared the results obtained using deep learning models to the ones using Bayesian networks. The accuracy of the obtained deep learning models ranged from 67.1% for the first-year students up to 94.3% for the third-year students. |
| first_indexed | 2024-04-13T11:54:15Z |
| format | Article |
| id | doaj.art-d12d22662eb94f469d1661e011fb36e6 |
| institution | Directory Open Access Journal |
| issn | 1826-6223 1971-8829 |
| language | English |
| last_indexed | 2024-04-13T11:54:15Z |
| publishDate | 2020-05-01 |
| publisher | Italian e-Learning Association |
| record_format | Article |
| series | Je-LKS: Journal of E-Learning and Knowledge Society |
| spelling | doaj.art-d12d22662eb94f469d1661e011fb36e62022-12-22T02:47:58ZengItalian e-Learning AssociationJe-LKS: Journal of E-Learning and Knowledge Society1826-62231971-88292020-05-0116110.20368/1971-8829/1135192Deep learning approach for predicting university dropout: a case study at Roma Tre UniversityFrancesco Agrusti0Mauro Mezzini1Gianmarco Bonavolontà2Roma TRE UniversityRoma Tre UniversityRoma Tre UniversityBased on current trends in graduation rates, 39% of todays young adults on average across OECD countries are expected to complete tertiary-type A (university level) education during their lifetime. In 2017, an average of 10.6% of young people in the EU-28 were early leavers from education and training. Therefore the level of dropout in the scenery of European education is one of the major issue to be faced in a near future. The main aim of the research is to predict, as early as possible, which student will dropout in the Higher Education context. The accurate knowledge of this information would allow one to effectively carry out targeted actions in order to limit the incidence of the phenomenon. The recent breakthrough on Neural Networks with the use of Convolutional Neural Networks architectures has become disruptive in AI. By stacking together tens or hundreds of convolutional neural layers, a “deep” network structure is obtained, which has been proved very effective in producing high accuracy models. In this research the administrative data of about 6000 students enrolled from 2009 in the Department of Education at Roma Tre University had been used to train a Convolutional Neural Network based. Then, the trained network provides a predictive model that predicts whether the student will dropout. Furthermore, we compared the results obtained using deep learning models to the ones using Bayesian networks. The accuracy of the obtained deep learning models ranged from 67.1% for the first-year students up to 94.3% for the third-year students.http://www.je-lks.org/ojs/index.php/Je-LKS_EN/article/view/1135192University DropoutDeep LearningConvolutional Neural NetworkEducational Data MiningBayesian Network |
| spellingShingle | Francesco Agrusti Mauro Mezzini Gianmarco Bonavolontà Deep learning approach for predicting university dropout: a case study at Roma Tre University Je-LKS: Journal of E-Learning and Knowledge Society University Dropout Deep Learning Convolutional Neural Network Educational Data Mining Bayesian Network |
| title | Deep learning approach for predicting university dropout: a case study at Roma Tre University |
| title_full | Deep learning approach for predicting university dropout: a case study at Roma Tre University |
| title_fullStr | Deep learning approach for predicting university dropout: a case study at Roma Tre University |
| title_full_unstemmed | Deep learning approach for predicting university dropout: a case study at Roma Tre University |
| title_short | Deep learning approach for predicting university dropout: a case study at Roma Tre University |
| title_sort | deep learning approach for predicting university dropout a case study at roma tre university |
| topic | University Dropout Deep Learning Convolutional Neural Network Educational Data Mining Bayesian Network |
| url | http://www.je-lks.org/ojs/index.php/Je-LKS_EN/article/view/1135192 |
| work_keys_str_mv | AT francescoagrusti deeplearningapproachforpredictinguniversitydropoutacasestudyatromatreuniversity AT mauromezzini deeplearningapproachforpredictinguniversitydropoutacasestudyatromatreuniversity AT gianmarcobonavolonta deeplearningapproachforpredictinguniversitydropoutacasestudyatromatreuniversity |