Abstract:

Based on current trends in graduation rates, 39% of today’s young adults on average across OECD (2014) countries are expected to complete tertiary-type A (university level) education during their lifetime. In 2017, an average of 10.6% of young people (aged 18-24) in the EU-28 were early leavers from education and training (Eurostat, 2017). Over 3 million young people in the European Union (EU) had been to university or college but had discontinued their studies at some point in their life, according to a survey of 2016. 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 (HE) 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.

Today, Artificial Intelligence (AI) is being employed to replace human activities that are repetitive, for example, in the autonomous driving field or for the image classification task. In these areas AI competes with man with quite satisfactory results and, in the case of HE dropout, it is extremely unlikely that an expert teacher will be able to "predict" the student's educational success based only on the data provided by administrative offices.

The recent breakthrough on Neural Networks (Krizhevsky, 2012) with the use of Convolutional Neural Networks (CNN) 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 6000 students enrolled from 2009 on in the Education Department at Rome Tre University had been used to train the CNNs. Then, the trained network provides a probabilistic model that indicates, for each student, the probability of dropping out. We used several types of state-of-the-art CNNs (Szegedy et al., 2017; He et al., 2016), and their variants, in order to build the most accurate model for the dropout prediction. The accuracy of the obtained models, ranged from 67.1% for the first year student’s up to 90.9% for the second year students. With the use of more data, for example students’ career data, we could develop more accurate dropout prediction models.

References:
[1] Eurostat (2017). Early leavers from education and training. Retrieved from: https://ec.europa.eu/eurostat/statistics-explained/index.php/Early_leavers_from_education_and_training#Overview on December, 6th, 2018.
[2] He, K., Zhang, X., Ren, S., & Sun, J. (2016, October). Identity mappings in deep residual networks. In European conference on computer vision (pp. 630-645). Springer, Cham.
[3] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097-1105).
[4] OCSE (2014). Education at a Glance 2014: OECD Indicators, OECD Publishing.
[5] Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. A. (2017, February). Inception-v4, inception-resnet and the impact of residual connections on learning. In AAAI (Vol. 4, p. 12).

Keywords:

University dropout, convolutional neural networks, artificial intelligence.