Car Smart

• 

  Homepage

• 

  Final page with car's predicted price

Inspiration

The need for a transparent and accurate car pricing tool inspired me. I wanted to leverage machine learning to provide car owners and buyers with a reliable way to estimate vehicle values.

What it does

Car Smart predicts the price of a car based on various factors such as brand, year, mileage, fuel type, transmission, exterior and interior color, accident history, and title status.

How I built it

I used Python and Flask for the backend, with TensorFlow to build and train my machine learning model. We also utilized LabelEncoder to handle categorical data and ensure smooth data processing. The frontend uses HTML and CSS to create a user-friendly interface.

Challenges I ran into

Handling categorical data dynamically and ensuring the model's accuracy were significant challenges. I also faced issues with encoding data and integrating the model with our Flask backend.

Accomplishments that I'm proud of

I successfully built and deployed a working predictive model that integrates seamlessly with a user-friendly web interface. My biggest accomplishment is creating a tool that could genuinely help users make informed decisions about car prices.

What I learned

I learned a lot about machine learning model integration, handling and preprocessing data, and the importance of user experience in web applications. I also deepened my knowledge of Python, Flask, and TensorFlow.

What's next for Car Smart

I'm planning to enhance the model's accuracy by incorporating more data and refining my algorithms. Future updates might include a feature to provide market trends and analysis, making Car Smart an even more comprehensive tool for users.

Built With

• flask
• python
• tensorflow