In this project, I worked to understand the results of an A/B test run by an e-commerce website. The company developed a new web page in order to try and increase the number of conversions. My purpose is to help the company understand if they should implement the new page, keep the old page, or maybe even run the experiment longer before making a decision.
Create a Python environment in Jupyter Notebook with the following packages:
- pandas
- numpy
- random
- matplotlib.pyplot
- statsmodels.api
- scipy
- datetime
- and also
%matplotlib inlineandrandom.seed(42)
Find any typos? Have another resource you think should be included? Contributions are welcome.
First, fork this repository.
Next, clone this repository to your desktop to make changes.
$ git clone https://github.com/ccaddel/a_b_test_conversions.git
$ cd a_b_test_conversions
Once you've pushed changes to your local repository, you can issue a pull request by clicking on the green pull request icon.
Instead of cloning the repository to your desktop, you can also go to README.md in your fork on github.com, hit the Edit button (button with the pencil) to edit the file in your browser, then hit the Propose file change button, and finally make a pull request.