Early Warning System for Student Disengagement
Identify students who are drifting away from a course early enough for someone to intervene, using engagement signals rather than protected characteristics. The fairness analysis is not an appendix here, it is the core of the work.
Intermediate
A small team, or one strong student willing to learn something new.1 semester, 2 students
5 to ship
3 optional extrasSuggested stack
What you should ship
- Feature pipeline from engagement signals such as submission timing, attendance and platform activity
- Risk model validated on a cohort not used in training, with precision and recall at the operating threshold
- Fairness audit reporting error rates separately by gender, background and entry qualification
- Instructor dashboard listing at risk students with the contributing factors named
- Written policy on data use, retention, access and what the system must never be used for
If you have time left
- Recommending which specific intervention historically helped students with a similar profile
- Weekly trend showing whether risk is rising or falling per student
- Simulation of how much earlier intervention could occur compared with current practice
The problem
Students who fail a module usually show signs weeks earlier: submissions arriving later, attendance thinning, activity dropping. By the time a result is recorded, the moment to help has passed.
What you build
A feature pipeline over engagement signals, a risk model, a fairness audit and a dashboard that names its reasons.
The constraint that defines the project
Use behaviour, not identity. Gender, ethnicity, nationality and socioeconomic proxies must not be inputs, and you must still audit outcomes across those groups, because a model trained on engagement can easily encode them indirectly. A student working two jobs shows the same signals as a disengaged one, and a system that cannot tell the difference will systematically flag the wrong people.
Why explanation is mandatory
An instructor given a list of names and no reasons will either ignore it or act on it badly. Naming the contributing factors, such as three consecutive late submissions and no platform activity for two weeks, is what makes the output usable and challengeable.
Data and ethics
Use anonymised historical data with institutional approval, or a public educational dataset. This project touches real students' records and needs your institution's ethics process. Say plainly in the report that the tool supports human judgement and must never feed an automated decision.
Scope warning
Prediction and presentation only. Do not build automated messaging to students.
Ideas and guidance, not finished projects
These are project ideas and scoping guidance, published free for students to use as a starting point. I do not build, write, or sell final-year projects, and I do not complete coursework for anyone. Take an idea, make it yours, and build it.
Not sure this one fits you?
I help students pick an idea that matches their skills and their deadline, then scope it down until it is finishable. Guidance only, never done for you.
Stuck on something specific?
Writing only gets you so far. If you want an answer to your situation rather than the general case, book a session and we will work through it together. Every session is free; a few slots open each week.
Follow along
New writing, resources and project ideas land here first.