Learning Analytics

The Society for Learning Analytics Research (SoLAR, 2011) defines learning analytics as the “measurement, collection, analysis and reporting of data about learners and their contexts, for purposes of understanding and optimizing learning and the environments in which it occurs.”

The School of Mathematics & Science regularly carries out learning analytics projects with the aim of improving student learning.

Identifying Students At-Risk for Failure

One ongoing project uses machine learning to identify students at-risk for failure.  Patterns discovered in academic results, attendance records, and other data are used to flag at-risk students so that an intervention can take place early in the semester.  Examples of intervention include peer tutoring, and additional coaching by lecturers.

Statistics and Analytics for Engineers

MS's Statistics and Analytics for Engineers module is featured by Knime as one of their external courses. 

Module Aims:
This module aims to provide engineering students with an introduction to statistics and data analytics (DA). DA is a competency that cuts across the Skills Framework of many sectors related to engineering. With today’s technology, engineers can harness the power of statistics and DA to analyse data and generate insights to support decision-making. The topics in statistics include descriptive statistics, probability, random variables and probability distributions, sampling distributions, and estimation. The topics in data analytics include a brief overview of data mining, cluster analysis, decision tree classifier, and linear regression. Software tools (such as Minitab Express and KNIME) are used throughout for hands-on exercises.

Teaching Methods/Learning Tasks:
Flipped-classroom is adopted as the teaching method. Weekly, students will complete 1 hour of online lecture out of class, mostly via short videos.  This is followed by 3 hours of tutorial in class, where students will solve tutorial problems and participate in activities with their peers, under tutor’s guidance and facilitation. As far as possible students will practice using a software tool for each procedure/technique learned. Students will also learn to interpret results and graphs through examples and exercises in the module.

Lecturer: Chia Tien Chern and Kok-Mak Chew Pheng

Click here for more information.