Boston AirBnb Data Analysis

Analysing the Boston Data for Airbnb. The blog post is here @aj455/boston-airbnb-data-analysis-43c38b1cfae5"">https://medium.com/@aj455/boston-airbnb-data-analysis-43c38b1cfae5

Motivation

This project was created as part of Udacity’s Data Scientist nanodegree. Here I have analyzed Boston Airbnb Open Data following CRISP-DM methodology. Airbnb data for other cities have the same format. So the same understandings and code can be applied to Airbnb dataset of any other city.

The business questions which I have tried to answer in this project are as follows:

• Most common price listings for AirBnb?
• What is the relation between price and property type?
• Which room types in each neighbourhood have high prices?
• What are the top 5 amenities?

Dataset Used:

Kaggle Boston AirBnb data https://www.kaggle.com/airbnb/boston.
The following Airbnb activity is included in this Boston dataset:

• Listings, including full descriptions and average review score
• Reviews, including unique id for each reviewer and detailed comments
• Calendar, including listing id and the price and availability for that day

Libraries Used:

1. Numpy
2. Pandas
3. Matplotlib pyplot
4. Seaborn
5. Sklearn

Language and Frameworks used:

Python3, Jupyter Notebook

Results

• The most common price listings are in the 50-200 USD range with the highest price being 4000 dollars
• Property types like bread and breakfast are the cheapest and room types which are shared are generally cheapest
• Entire homes/ apartments are the most costly in each neighbourhood while South boston Waterfront is the most expensive neighburhood at 306 dollars.
• Top 5 amenities are Wireless Internet, Heating, kitchen, Essentials, Smoke detector

Deployment:

Using Google Collab, but can also be run using jupypter notebook command.

Acknowledgements

Thanks to Kaggle and AirBnb for the dataset and Udacity for the course.