Academic Success Monitor (ASM)

The project team will support you throughout 2025 through:

• User guides and helpful videos through the ASM Current Students Website
• End-of-term surveys
• Drop-in sessions – just email us with a request at [email protected]
• Feedback form to report any issues or suggest improvements!

We will respond to your email or form submissions within 2 business days.

Keep an eye out in your emails for more information on where to go for help from 2026 onwards!

The Academic Success Monitor provides you with a range of insights, including:

1. How you are going in the course and what level of support you might need through a machine learning-driven prediction.
2. Your level of digital engagement compared to the average of your cohort.
3. A list of factors that may be contributing to the analysis of how you are progressing in the course.
4. A list of the five most accessed resources/activities in the course during the past seven days.
5. Real-time notifications of incoming communications and updates.

The ASM also provides AI-generated messages with further details about the level of support you might need and suggestions to help you maximise your academic success. You will be able to take actions as appropriate, follow up on them, and provide immediate feedback.

The ASM currently leverages your existing student and course data, including digital engagement patterns in Moodle, academic performance, background information from Student System Information (SiMs), and the history of your course. This is educational data that is already available through UNSW systems.

Your educational data is streamlined and analysed to provide insights and alerts tailored to your individual needs. Educational data from third-party providers such as Echo360, Teams, Inspera, and other relevant sources, such as myExperience data, will be gradually integrated into the system.

The monitor relies on your digital engagement data, such as when you log in, click, or view a digital resource. However, this data is scaled against the typical behaviours of your current course cohort. Any information that is not online will not be captured by the ASM, so current data insights may not provide a full picture of your learning or the learning environment.

The machine learning prediction of how you are tracking in the course is a possibility, not a certainty. Think of it like a weather forecast – it might show a 30% chance of rain, but it is up to you to decide whether to bring an umbrella or not!

Current testing of the machine learning model shows that, among all students who failed a course, 80% were predicted as needing urgent support or falling behind. Among all students predicted as needing urgent support or falling behind, 61% actually failed.

The main purpose of the prediction is to help you understand what level of support you might need earlier in the teaching period. This allows UNSW to recommend free resources as a starting point or to reach out if there is any concern. Bearing in mind the limitations, you should use these insights in the context of your own circumstances and take appropriate actions to seek support from your teaching staff, central support services, or faculty support services.

If you have concerns, please reach out to the course convenor or the project team at [email protected].

There are three types of messages you may receive from the ASM:

• Your course convenor may send a message to you via the ASM, which may sometimes be supported by AI
• AI-generated messages based on your personal circumstances that appear in the ASM application dashboard or,
• AI-generated messages based on your personal circumstances that are emailed to your zID

All the prompts feeding the GenAI have been reviewed and endorsed by a range of entities, including the project’s Steering Committee, Learning Analytics Working Group, UNSW Support Services, Student Engagement team, and UNSW Legal and Compliance.

The monitor is personal to you and is only accessible by you. The use of this tool aligns with UNSW’s current ethical standards and complies with the current student privacy statement for the staged roll-out throughout 2025.

Your convenor will see a similar view, however displayed differently, as it will be used in supporting their activities in managing the entire course cohort.

The student-facing version aims to help you track your own digital involvement in the course, highlight frequently accessed activities by your peers, and provide personal alerts if your engagement pattern suggests risk, along with suggestions to maximise your chances of academic success in the course.

The staff-facing version will assist course convenors in better understanding students' needs and can encourage more proactive support within large classes. It will help course convenors track digital engagement and enhance the level of support provided, creating more opportunities for your success.

Learning analytics has been used and proven beneficial to student learning and engagement in many Australian universities and overseas. For example, the University of Sydney has been using SRES (The Student Relationship Engagement System) since 2012, while Deakin University introduced Genie, a digital personal assistant tool for students, in 2018. Other examples include RiPPLE by the University of Queensland and iLEARN Insights by Macquarie University.