I was inspired to build this project because car prices can vary widely, making it hard for buyers and sellers to know what a vehicle is worth. I wanted to make those estimates easier to explore with a simple web app.
I built a Flask application that uses vehicle details such as brand, year, mileage, fuel type, and transmission to estimate a car’s price. The site also presents model and dataset information, offers light and dark themes, and updates the estimate as users complete the form.
While building it, I learned how to connect a machine-learning pipeline to a web interface, validate user input, and present model results in a clear way. One challenge was making sure the page’s CSS, JavaScript, and prediction API all worked together—especially when the page was opened through a static server instead of Flask. I addressed that by checking the assets and API routes and trying a sample prediction through the app.
Built With
- css
- csv
- data-visualization
- flask
- html
- javascript
- joblib
- machine-learning
- numpy
- pandas
- python
- regression
- responsive-design
- rest-api
- scikit-learn
Log in or sign up for Devpost to join the conversation.