This project focuses on exploring some of business questions relted to Boston and Seattle Airbnb data.

Boston is located on the east coast of the US, whereas Seattle is located on the west coast. If we compare the weathers, this is what we see:

Boston, Massachusetts

Summer High: the July high is around 82.4 degrees

Winter Low: the January low is 19.2

Rain: averages 47.4 inches of rain a year

Snow: averages 48.1 inches of snow a year

Seattle, Washington

Summer High: the July high is around 75.8 degrees

Winter Low: the January low is 37

Rain: averages 38 inches of rain a year

Snow: averages 4.6 inches of snow a year

Source: https://www.bestplaces.net/climate/?c1=55363000&c2=52507000

As we can see, Seattle is a slightly more comfortable place to visit. Let’s see what we can infer using the Airbnb data.

This project is done on anaconda platform using jupyter notebook jupyter notebook. The detailed instruction of how to install anaconda can be found here. To create a virtual environment see here

in the virtual environment, clone the repository :

git clone https://github.com/abhishek-jana/AirBnb-housing-project.git

Packages used for this project are:

Numpy
Pandas
Matplotlib
Seaborn

Next, use the following command to install the necessary packages:

cd <pat to Airbnb-housing-project>
pip install -r requirements.txt

To install the dependencies.

The dataset for the project can be downloaded from here.

This projects aims to solve 4 business questions related to Boston and Seattle data.

Question 1: Which place is cheaper to stay? Boston or Seattle.

Question 2: What is the best time to visit these places?

Question 3: Which city is more popular with visitors?

Question 4: What are the popular areas to stay and what is the recommended type of housing?

In the repository please look into the jupyter notebook "What is your next destination? Boston or Seattle!.ipynb" for the analysis.

There are four types of datasets used for this project. "Boston_listing.csv", "Seattle_listings.csv", "Boston_calendar.csv" and "Seattle_calendar.csv".

The last two datasets has date, listing_id, price, avilable columns. If we compare the average housing price between Boston and Seattle using "price" column of the datasets we can determine which place is cheaper (answer to Question 1).

Using the "date" and "price" columns we can find out how the pricing changes throughout the year (answer to Question 2).

We can also find out the monthly availibility of the properties using the "available" column. Using this information we can answer Question 3.

The first two datasets gives us information on how the pricing changes with the property type, bedrooms, bathrooms, neighbourhood, zipcode etc. In this project I tried to find out the relation between neighbourhood and price and between property type and price. These two analysis can help determine Question 4 which aims to find out the popular places to stay in Boston/Seattle and finding recommended housing on these cities.

The "image" folder contains varius plots related to the analysis which can also be found in the jupyter notebook.

I found out that in terms of weather conditions, housing prices Seattle is a better place to travel compared to Boston.

From this analysis, the conference holders can also decide what's the ideal time to hold big events in Boston/Seattle.

Please look into the notebook for detailed analysis.

In future work, I will show how to predict the Airbnb price using machine learning.

I am thankful to Udacity Data Science Nanodegree program for motivating me in this project.

I am also grateful to Kaggle and Airbnb for making the dataset publicly available.