-
A live demonstration of the Fair Pay-AI backend processing a salary prediction request.
Inspiration
The Inspiration As a BCA student, I noticed that many early-career professionals struggle to negotiate salaries because they lack objective data. I was inspired to build Fair Pay-AI to bridge this gap using Machine Learning, providing a simple yet powerful tool for compensation transparency.
How I Built It
Machine Learning: Developed using Python and Scikit-Learn. I implemented a Linear Regression model trained on professional features (Experience, Age, and Skill Scores). Backend: Built with Fast API to create a high-performance REST API that processes user input and returns real-time JSON predictions. Frontend: A clean, responsive interface designed with HTML5 and CSS3, allowing users to input their data easily. Data Handling: Used NumPy for efficient array manipulation and data preparation before feeding it into the model.
Challenges I Faced
The biggest challenge was ensuring the seamless flow of data between the HTML form and the Python backend. I encountered initial issues with data type mismatches, which I resolved by implementing strict type-casting for the input features (int and float) to ensure the model. predict() function received the correct format.
What I Learned
During this hackathon, I mastered the process of taking a Machine Learning model from a script to a live web service. I gained deep experience in API routing, model serialization, and building user-centric AI tools.
