Inspiration
The inspiration for this project comes from the need to optimize study plans for individuals with varying attention spans and learning needs. By using real-world data and predictive models, the goal is to create personalized and efficient study plans that adapt to the user’s ADHD severity, educational stage, and age group.
What it does
The project uses machine learning to predict optimal study session durations and break intervals based on user-provided data. It dynamically adjusts the study plan by considering ADHD severity, education, and age, ensuring that users can achieve maximum focus and productivity during their study sessions.
How we built it
Dataset: We started with a dataset containing participant information, including educational stage, age group, ADHD severity, and their preferred study and break durations. Machine Learning Models: Trained linear regression models using Scikit-learn to predict: Optimal study session duration. Break interval for maximum efficiency. Adjustments: Incorporated dynamic adjustments based on ADHD severity, education, and age to fine-tune session durations and splits. Interactive Interface: Enabled user input for personalization and predicted results based on real-time data.
Challenges we ran into
Data Scaling: Mapping categorical values (like educational stage and ADHD severity) into meaningful numerical scales while maintaining interpretability. Model Generalization: Ensuring the trained models perform well for unseen data and edge cases. Dynamic Adjustments: Balancing the impact of ADHD severity, education, and age scales to create realistic session plans. User Experience: Designing an intuitive interface for users to input data and view personalized study plans.
Accomplishments that we're proud of
Successfully trained predictive models for session duration and break intervals. Designed a severity adjustment mechanism that incorporates ADHD, education, and age to personalize study plans. Developed a user-friendly script that dynamically calculates study splits and provides actionable insights. Created a scalable framework that can be extended with additional user data for better predictions.
What we learned
Feature Engineering: The importance of properly scaling and encoding data to improve model performance. Personalization: How to use machine learning to cater to diverse user needs based on demographic and behavioral data. Iterative Improvement: Refining models and logic through testing and validation with edge cases.
What's next for STAY App
Visualization: Integrate graphical insights, such as study plans and focus patterns, to enhance user experience. Mobile Application: Build a mobile app interface to make the tool more accessible. Expanded Dataset: Incorporate additional demographic and behavioral features for improved accuracy. AI Recommendations: Provide real-time feedback to users based on their progress and engagement levels.
Log in or sign up for Devpost to join the conversation.