erolgelbul / car_sales_ann Goto Github PK

A model that predicts how much the customer will potentially pay when purchasing a new car.

If you would like more information on the project, please check out my blog post.

(back to top)

• Since this is a prediction and it is a continual value (purchase amount) the problem at hand is a regression problem.
• After 20 epochs the error dropped significantly. If the model is limited to 30 epochs instead of a 100, that will be more efficient.

(back to top)

I used Jupyter Notebook. I recommend installing Anaconda.

First create an account on Anaconda Cloud

$ conda install anaconda-client

pip install anaconda-client

pip install git+https://github.com/Anaconda-Server/anaconda-client

$ anaconda login

Test your login with the whoami command:

$ anaconda whoami

For a complete tutorial on building and uploading Conda packages to Anaconda Cloud visit the documentation page.

• http://docs.anaconda.org/
• https://anaconda.org

After you have Anaconda installed, you need to download Jupyter Notebook application within Anaconda.

1. Launch Jupyter Notebook.
2. Go to File, then Open.
3. Open the file: predicting_car_sales.ipynb.
4. Press CTRL + Enter to run a single cell.
5. The output of a specific cell will be presented below.
6. If anything goes wrong, just reset the kernel by pressing 0, 0.

(back to top)

If you would like to add any extra features to the optimisation simulation, feel free to fork and create a pull request. Thank you!

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

(back to top)

Erol Gelbul - Website - [email protected]

Project Link: Car Sales

(back to top)