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.
- 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.
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.
After you have Anaconda installed, you need to download Jupyter Notebook application within Anaconda.
- Launch Jupyter Notebook.
- Go to
File
, thenOpen
. - Open the file:
predicting_car_sales.ipynb
. - Press
CTRL + Enter
to run a single cell. - The output of a specific cell will be presented below.
- If anything goes wrong, just reset the kernel by pressing
0
,0
.
If you would like to add any extra features to the optimisation simulation, feel free to fork and create a pull request. Thank you!
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature
) - Commit your Changes (
git commit -m 'Add some AmazingFeature'
) - Push to the Branch (
git push origin feature/AmazingFeature
) - Open a Pull Request
Erol Gelbul - Website - [email protected]
Project Link: Car Sales