Inspiration

Scheduling employee shifts is often chaotic — managers struggle to balance workloads, employee preferences, and last-minute changes. We wanted to build something that uses AI intelligence to remove manual pain, improve fairness, and optimize productivity.

What it does

ShiftSmart automatically creates optimal shift schedules using AI. It analyzes data like workload, employee skills, attendance, and preferences to assign shifts fairly and efficiently. It also reschedules automatically when someone calls in sick, ensuring smooth operations.

How we built it

We used Spring Boot for the backend API, React.js for the frontend, and PostgreSQL as the database. AI scheduling logic was implemented in Python using scikit-learn for prediction models and pandas for data processing. We containerized the app with Docker and deployed it on AWS EC2 for scalability.

Challenges we ran into

Integrating AI models with real-time scheduling data

Ensuring fairness and avoiding employee bias in algorithm design

Handling large datasets efficiently under time constraints

Accomplishments that we're proud of

What we learned

We learned how to combine AI, backend logic, and UI/UX seamlessly to create a real-world productivity solution. We also learned the value of collaboration, version control, and quick iteration under a hackathon timeline.

What's next for ShiftSmart – AI-Driven Workforce Shift Optimization

Share this project:

Updates

posted an update

We developed a Spring Boot backend API to manage scheduling logic, a React.js frontend for intuitive user interaction, and a PostgreSQL database for data management. Our AI scheduling engine was built in Python, using scikit-learn for prediction models and pandas for data analysis. We containerized the app with Docker and deployed it on AWS EC2 for scalability and reliability.

Log in or sign up for Devpost to join the conversation.