https://github.com/dopebiscuit/applai-final-project
ApplAI ML workshop '23 final project, it's a customer segmentation project using clustering, deployed using streamlit.
https://github.com/dopebiscuit/applai-final-project
clustering-algorithm final-project machine-learning streamlit
Last synced: 2 months ago
JSON representation
ApplAI ML workshop '23 final project, it's a customer segmentation project using clustering, deployed using streamlit.
- Host: GitHub
- URL: https://github.com/dopebiscuit/applai-final-project
- Owner: DopeBiscuit
- License: mit
- Created: 2023-09-18T15:22:02.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2023-09-18T15:41:01.000Z (almost 3 years ago)
- Last Synced: 2025-03-31T14:59:45.219Z (about 1 year ago)
- Topics: clustering-algorithm, final-project, machine-learning, streamlit
- Language: Jupyter Notebook
- Homepage:
- Size: 663 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ApplAI Final Project
### This is a Customer Segmentation project.
**Problem Statement**: Owners of a mall want to segment their customers based on the data they have collected about them, the data is located in the CSV "Mall_Customers.csv" file.
You can find all my steps to deal with the data in the Notebook file. First the pre-processing then data representation, then I proceed with my assumptions and try out different models to check their efficiency, throughout the notebook you will find the Comment blocks explaining my thought process, beliefs, and conclusions. The code is also commented on for ease of readability.
The clustered data is then deployed on a website using Streamlit library, the data is not deployed in the form of a dashboard due to a lack of features and possible analytics, after approval of my mentor I deployed it in a form submission manner, where you populate a form simulating a customer, and you will be assigned to the proper cluster, interactive plots are available on the site.
**To try the website download both the "Classifier.py" and the "Customer_Segmentation_model" and then install the required dependencies in the Python file, run the Python file using Streamlit, and test it out.**