Adaptive Study Planner with Spaced Repetition
A study tool that schedules review based on what a learner actually forgets rather than a fixed timetable, using a spaced repetition algorithm and a difficulty estimate per item. Approachable enough for a solo project and still contains a real algorithm.
Beginner
Achievable by one student in a semester with familiar tools.1 semester, 1 to 2 students
5 to ship
3 optional extrasSuggested stack
What you should ship
- Content model supporting topics, items and prerequisite relationships between topics
- Scheduling algorithm implementing spaced repetition with per item difficulty adjustment
- Review interface with self rated recall feeding back into the schedule
- Progress dashboard showing retention estimates per topic and upcoming workload
- Simulation comparing your schedule against fixed interval review, using synthetic learners with a defined forgetting curve
If you have time left
- Question generation from supplied notes
- Prerequisite awareness so a weak foundation topic is surfaced before its dependents
- Workload smoothing so review days do not spike before an assessment
The problem
Students revise by rereading, which feels productive and produces poor retention. Spaced repetition works considerably better and the reason it is not universal is that scheduling by hand is tedious.
What you build
A study system where each item has an estimated difficulty and a next review date, updated after every review based on how well the learner recalled it. Add prerequisite relationships between topics so the system can tell that struggling with one topic is caused by a weakness in another.
Why this suits a smaller team
The scope is well defined, the algorithm is documented in the literature and implementable, and the interface is straightforward. It is a project a strong individual can complete and defend, which is not true of most machine learning topics.
The evaluation problem, and how to solve it
You cannot run a controlled study on real students in a semester. What you can do is simulate: define synthetic learners with a known forgetting curve, run your scheduler and a fixed interval baseline against them, and report retention per unit of study time. State clearly that this is a simulation, and it is a perfectly respectable result.
The hard part
Prerequisite modelling. Working out that a learner keeps failing a topic because an earlier one never consolidated, and acting on that, is where this becomes more than a flashcard application.
Scope warning
Do not build a content library. Let users add their own material, or import from an existing format.
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.