Sign in

Comparison of Hotel Homes in Boston and Seattle

Holiday Homes in Seattle or Boston?

Living in Minnesota amidst the pandemic? Have a wanderlust that needs to be fulfilled?

You are in luck, the two cities that are hot spots for tourists are Seattle and Boston city. In this age of technology, Airbnb has provided homeowners who have the ability to turn their homes into instant hotels. If you want to get a bang for your buck, you need data to make informed choices. I am have been thinking about what you will wanna know before booking that ticket to decide where you wanna go.

And as such, the three questions that I attempt to answer through the Airbnb data obtained from Kaggle are:

  1. Comparing Boston and Seattle Airbnb listings, which city is more expensive for a family of 4 and for a couple?
  2. Some hotel homes offer affordable daily prices but excluding the cleaning fee. Within the 2 cities, does paying a cleaning fee always ensure that the environment is cleaner? In other words, are cleaning fees justified?
  3. Which are the 5 most popular neighborhoods in Boston and Seattle respectively based on the review score rating?

— — — — — — — — — — — — — — — — — — — — — — — — — — — — — — —

Comparing Boston and Seattle Airbnb listings, which city is more expensive for a family of 4 and for a couple?

To answer the first question, we have to compare apple with apple. The basis of comparison must be as similar as possible. As such, the price per night and cleaning fees are added to form the ‘daily cost’ variable should the traveller stay for less than a week. The dataset is split further down to different property types for a fairer comparison.

For handling the missing data, any rows with missing data in the property type are drop immediately because imputing a mean value for the price will not make sense. Luckily for this data set, the property type is almost always present. Any row with a cleaning fee missing is replaced with 0 because some homeowners already incorporated those fees into their price.

The results are as follows:

Comparison of cost of Holiday Home for a couple
Comparison of cost of Holiday Home for a couple
Comparison of cost of Holiday Home for family of four

For a family of four, hotel homes in Boston are consistently priced higher than in Seattle for the category of properties that are present in 2 cities. It can also be seen that the hotel homes in Seattle seem to provide a myriad of experiences like Camper/RV and tent stay.

Comparison of cost of Holiday Home for a couple

For a couple, hotel homes in Boston are higher in daily cost as well.

Hence, I conclude that housing prices in Boston are higher than that in Seattle. And Seattle seems to take a win on the cost aspect.

— — — — — — — — — — — — — — — — — — — — — — — — — — — — — — —

Within the 2 cities, does paying a cleaning fee always ensure that the environment is cleaner?

Moving on to the 2nd business question, is the cleaning fee always justified? Does paying the owner a cleaning fee correspond to cleanliness indicated by the cleanliness rating?

Firstly, to clean the dataset, any row with a cleaning fee missing is replaced with 0 because some homeowners already incorporated those fees into their price. any row with the review_scores_cleanliness missing is removed because that is our label dataset. Then we concatenate the listing data from Boston and Seattle to form one data frame for easy analysis.

By plotting a scatter plot, we arrived at the following plot. At the primary glance, this tells us that charging a higher cleaning fee tends to mean that the cleanliness rating is higher.

Scatterplot of cleanliness score vs cleaning fee.

How effective is the cleaning fee in predicting the cleanliness score? For this, a linear regression summary statistics may be sufficient in telling us that.

Summary Statistics for linear regression of cleanliness score against the cleaning_fee

Based on the F-statistics probability, the linear regression using cleaning fee as the independent variable is useful in predicting the dependent variable. The p-value for the independent variable is lesser than the 0.05 level of significance. meaning that the cleaning fee is significant in predicting the cleanliness score. For every dollar increase in a cleaning fee, the cleanliness score increase by 0.0016. Hence, the cleaning fee does mean that the hotel homes are cleaner than hotels that do not collect cleaning fees on average.

— — — — — — — — — — — — — — — — — — — — — — — — — — — — — — —

Which are the 5 most popular neighborhoods in Boston and Seattle respectively based on the review score rating?

Moving on to the last business question, which is the 5 most popular neighborhoods for Boston and Seattle respectively. Knowing this will help you choose the best neighborhood for the best experience possible.

First any rows with neighborhood_cleansed and review_scores_rating missing are dropped. The review score ratings are then grouped by the neighborhood and then averaged.

Finding the five most popular neighborhoods in Seattle and Boston using the review_scores_rating.

There you have it, the 5 most popular neighborhoods of Boston and Seattle.

Time to book your next ticket to Boston, Leather District. Here is a photo of your next home hotel:

Leather District, Boston.

Now you know where to go, pack your bag and book a ticket.

GitHub Repository: https://github.com/alanlee1994/assignment1_DS

Scoot! :)

Sharing and learning knowledge one step at a time.