Employee Salary Prediction

Inspiration Fair salary decisions are vital, yet manual processes are often biased and inconsistent. We wanted to build a smart, data-driven tool that helps HR teams make reliable and transparent salary predictions.

What it does The app predicts an employee's salary based on input factors like experience, education, job title, and location. Users enter the details via a clean Streamlit frontend and instantly receive an accurate prediction.

How we built it We used a Random Forest Regressor trained on a custom dataset. The pipeline includes preprocessing using ColumnTransformer and OneHotEncoder. The backend is built in Flask, and the frontend uses Streamlit for interactivity.

Challenges we ran into Managing the integration between Flask and Streamlit during local testing

Resolving encoding errors between model training and live prediction

Handling Streamlit deployment and dependency issues on limited resources

Accomplishments that we're proud of Successfully built and tested a full-stack ML application

Used pipeline-based modeling for clean, reusable code

Created a user-friendly UI that even non-tech users can navigate

What we learned We learned the importance of proper preprocessing, the power of pipelines in scikit-learn, and how to structure and deploy real-world ML apps using free tools effectively.

What's next for Employee Salary Prediction We plan to add resume parsing, visual analytics, and voice-based assistant features using Gen AI to create a complete AI-powered recruitment and HR tool.

Built With

• chatgpt
• flask
• github
• joblib
• pandas
• python-3.10
• render
• scikit-learn
• streamlit
• streamlit-community-cloud
• visual-studio-code