Here is an analysis of the Airbnb data by iplementing CRISP-DM and finding a solution to few questions with appropriate charts and dashboards.
You can also find my article about this analysis in my medium article provided in the link HERE
No external libraries are required to run the code here beyond the Anaconda distribution of Python. The code should run with no issues using Python versions 3.*.
This project motivation comes from Udacity's online course for Data Scientist Nanodegree project. The main interest to the project is finding a solution to the following questions.
- How does the listings vary according to the bedroom size and the type of the property?
- How is the interaction of host with their client affected based on their Acceptance rate, Response Rate and Response Time?
- What are the important features that estimates the price of a certain Property?
The above questions are the structure that defines the entire project.
There is a jupyter notebook available here to dealwith the above questions. The notebook follows the CRISP-DM process of understanding the business and the data, preparation of data, modelling and consequently, model evaluation. Markdown cells have been used to assist in walking through the thought process for individual steps.
The results of the project and the findings can be found in the code itself. It deals with the questions addressed in the motivation section.
Credits to Kaggle for providing the data(https://www.kaggle.com/airbnb/seattle/data) . You can find the licensing for the data and other descriptive information at the Kaggle link available. Also, I would like to extend my gratitude towards Airbnb and Udacity in my steps towards the project.