Sleep Nerd

• 

  Sleep Nerd Icon

Inspiration

Many people, especially college students, face rising stress and burnout but don't realize how daily habits like sleep, activity, and study load contribute. By the time stress becomes a crisis, it's often too late to easily course-correct.

What it does

Our mobile app tracks daily lifestyle inputs and uses a machine learning model (trained on real health and student stress datasets) to predict the user's stress level. It then uses a visual avatar to reflect their current wellbeing state alongside personalized, actionable feedback. Instead of generic advice, the app identifies exactly what's driving your stress that day and what to fix first.

How we built it

We built the core intelligence by training our stress prediction model on two real datasets covering sleep health and student stress factors, ensuring it's data-driven, not based on made-up statistics. This was integrated into an app that tracks user inputs and delivers personalized feedback through an interactive avatar.

Challenges we ran into

Integrating multiple datasets with different formats and ensuring the model could provide accurate, prioritized feedback in real time required significant testing and refinement.

Accomplishments that we're proud of

We're proud to have created a truly data-driven model trained on authentic health data and to have moved beyond generic wellness scores to deliver personalized, actionable insights that help users address stress before it escalates.

What we learned

We learned that real-time awareness of how daily habits affect stress is critical for prevention and that the quality and specificity of data directly impact how useful the feedback can be for users.

What's next for Sleep Nerd

We plan to enhance our model by incorporating more data on how occupation, age, and living conditions affect stress levels: allowing for even more accurate predictions and personalized feedback.

Built With

• python