Cruz-Jesus Frederico, Castelli Mauro, Oliveira Tiago, Mendes Ricardo, Nunes Catarina, Sa-Velho Mafalda, Rosa-Louro Ana
NOVA Information Management School (NOVA IMS), Universidade NOVA de Lisboa, Campus de Campolide, 1070-312, Lisboa, Portugal.
Heliyon. 2020 Jun 9;6(6):e04081. doi: 10.1016/j.heliyon.2020.e04081. eCollection 2020 Jun.
Understanding academic achievement (AA) is one of the most global challenges, as there is evidence that it is deeply intertwined with economic development, employment, and countries' wellbeing. However, the research conducted on this topic grounds in traditional (statistical) methods employed in survey (sample) data. This paper presents a novel approach, using state-of-the-art artificial intelligence (AI) techniques to predict the academic achievement of virtually every public high school student in Portugal, i.e., 110,627 students in the academic year of 2014/2015. Different AI and non-AI methods are developed and compared in terms of performance. Moreover, important insights to policymakers are addressed.
理解学业成绩是最具全球性的挑战之一，因为有证据表明它与经济发展、就业和国家福祉紧密相连。然而，关于这一主题的研究基于调查（样本）数据中使用的传统（统计）方法。本文提出了一种新颖的方法，利用最先进的人工智能（AI）技术来预测葡萄牙几乎每一名公立高中生的学业成绩，即在2014/2015学年的110,627名学生。开发了不同的人工智能和非人工智能方法，并在性能方面进行了比较。此外，还为政策制定者提供了重要见解。
