Artificial neural network-based learning analytics technique for employability and self-sustenance

Abstract

The growing global rate of unemployment buttresses the quest for functional and all-inclusive education as canvassed by the Sustainable Development Goal 4 (SDG 4). Employability of graduates and entrepreneurial skills for self-sustenance can be fostered through Learning Analytics (LA) - a pedagogical paradigm that inculcates data analytics and team work skills in learners. LA measures the learning process by collecting learning-related data, analyzing same, and reporting trends to stakeholders for adaptive learning solutions that improve learning experience and learning outcomes. Though there are many data science techniques for enhancing LA, artificial neural network stands out as a highly predictive data mining tool and machine learning technique. An Artificial Neural Network-based Learning Analytics (ANN-based LA) system uses regression analysis, pattern recognition, and predictive analytics to elicit robust information from learner’s data for informed decision making by education stakeholders. However, there are open issues confronting ANN-based LA systems such as system quality issues, prolonged time of training neural network, and the huge memory space requirements. This paper proposes an n-tier layered software architecture for tackling the quality indicator concerns while hoping that upcoming researchers will resolve the others. This way, ANN-based LA will be repositioned for delivering functional education that promotes graduate employment through the impartation of industry-relevant skills like data analytics and team work.

Keywords: Artificial Neural Network, Employability, Entrepreneurship, Learner-related Data, Learning Analytics, Sustainable Development Goal 4..