AI Competition

All competitions should be prepared in advance and conducted on the day of the competition.

Deadline to register: October 10, 2025

Teams must design an AI-based Smart Study Planner that helps students organize their study time effectively. The solution can be a mobile app, web app, or desktop application. The system should include AI/ML features such as:

• Personalized study schedule generation.
• Predicting optimal study times based on student habits.
• Providing reminders, workload balancing, and adaptive adjustments for upcoming exams.

Teams must design an AI-based system that tracks homework assignments, organizes tasks, and provides useful insights (e.g. deadline reminders, workload predictions).

Submission Guidelines 
Submissions must include:

• A functioning prototype or demo of the AI-based Smart Study Planner.
• A project report (maximum 5 pages) outlining the design, functionality, and technical approach.
• A presentation and demo (maximum 5 minutes) explaining the system’s features and AI components.

All submissions must be submitted to the competition drive (to be shared later)

Code of Conduct

• Respectful collaboration is expected. Any form of cheating, plagiarism, or misconduct will result in disqualification.
• Teams must adhere to ethical AI practices, ensuring their AI systems respect privacy and avoid bias in task prioritization.

Platform

• The system must run on either Windows, macOS, or Android/iOS platforms.
• Web-based applications should support major browsers (Chrome, Firefox, Safari).

Programming Languages

• Students can use any programming languages and frameworks suitable for their project (e.g. Python, JavaScript, Swift, Java).
• AI libraries such as TensorFlow, PyTorch, or Scikit-learn are allowed.

AI Integration
The project must include AI-based functionality such as:

• Study Schedule Optimization: Create personalized timetables based on subject load, exam dates, and student input.
• Workload Prediction: Forecast how much time different subjects or tasks will take based on historical patterns.
• Adaptive Reminders: Suggest breaks, revision cycles, and study sessions depending on performance and progress
   

Data Requirements

• Teams can use publicly available datasets (e.g. time management studies, student productivity datasets) or generate their own synthetic data.
• Data privacy must be respected, and no personally identifiable information (PII) should be used without consent.

User Interface
The system must provide a user-friendly interface where students can:

• Input their classes, exams, and deadlines.
• View a suggested personalized study plan.
• Receive reminders and recommendations.
   

Initial Review

• Judges will first review the project submission materials (report, code, and video) to ensure the basic requirements are met.
• Teams failing to meet submission requirements (e.g., missing project components, broken demo) may be disqualified before further testing.

Functionality Testing

• Judges will test the planner by adding different subjects, exam dates, and deadlines.
• The AI system will be evaluated on how well it organizes and tracks assignments.

Performance Testing

• Judges will assess how quickly the AI system processes data and responds to user inputs (e.g., how fast it can generate task predictions or prioritize assignments).
• Systems will also be tested for stability and error handling (e.g., how well they manage incomplete or incorrect inputs).

AI Performance Testing

• Judges will provide several scenarios (e.g., a student with a lot of work due soon, or a student with multiple long-term projects) to evaluate how well the AI adapts.
• Systems should demonstrate that they can learn and improve over time by making more accurate suggestions for task prioritization and time estimates.

Click here to register for the competition