As a co-convenor of MFAC1501 Foundations in 2024, I have been actively engaged in testing and giving feedback on this platform embedded within our Moodle course. The results of this pilot have yet to be analysed or published, however, I am engaged in further evaluation of this pilot for our course, and consulting in further development of these technologies. We are interested in furthering this insight to understand how these innovative tools could be utilised to better support students at academic risk in the MFAC1501 course in 2025.

Overview (this background information is taken from UNSW Education News here)

Data Insights for Student Learning and Support is a new UNSW strategic project being developed by the PVCESE Innovation Pillar. It aims to enhance the student experience by helping to reduce failure rates through early predictions of risk and monitoring student engagement in a course. It will also increase student and staff awareness of UNSW’s valuable support services, promoting effective and efficient uptake and impact. Students and staff will be alerted if a risk of academic failure is detected to enable prompt action to be taken to address the situation, and appropriate support will be suggested based upon individual student circumstances.
 
The project will be built in a modular approach. The first module is the Academic Success Monitor (ASM) which is being developed for course convenors, tutors, and students for early 2024. ASM uses a predictive machine learning model trained on historical data from learning and administration systems such as Moodle and SiMs. This can provide suggestions of potential academic risk based upon engagement in the digital learning environment that an academic or student can validate and act upon. Early testing of the model has revealed it can identify students at risk with a high level of confidence in the initial few weeks of a course, allowing enough time for a student to adjust their trajectory. Development and limited testing will continue during T3, 2023.