IIIT-B & UpGrad
Airbnb
Case Study
By: P Anand Rao
Himanya Ponaganti
Dipanshu Yadav
Suppose that you are working as a
data analyst at Airbnb. For the past
few months, Airbnb has seen a major
decline in revenue. Now that the
INTRODUCTION restrictions have started lifting and
people have started to travel more,
Airbnb wants to make sure that it is
fully prepared for this change.
OBJECTIVE
The different leaders at Airbnb want to understand
some important insights based on various attributes in
the dataset so as to increase the revenue.
PROBLEM STATEMENT
1. Which type of hosts to acquire more and where?
2. The categorization of customers based on their preferences.
• What are the neighbourhoods they need to target?
• What is the pricing ranges preferred by customers?
• The various kinds of properties that exist w.r.t. customer
preferences.
• Adjustments in the existing properties to make it more
customer-oriented.
3. What are the most popular localities and properties in New York
currently?
4. How to get unpopular properties more traction? and so on...
Data Cleaning and Preparation
• First, we have understood the data of the dataset in python.
• Then we have handled the missing values using median. Identified
equal number of null values in both last_review, and
reviews_per_month of around 20.55%. Also, identifies in name and
host_name.
• Then separated the columns of dataset into categorical and
numerical datatypes.
• Then we have imputed the categorical column with mode and
numerical column with median
• Then we have checked if there are any outliers in 6 continuous
columns and treated the using capping method.
• The graphs depicts the top 10 host who are
List of Top 10 earning more.
Host to Acquire • Michael is the top earner who is earning more and
he belongs to Manhattan.
Targeted
Neighborhood
• We can clearly comprehend
that most the people would
prefer to go these location / area
only.
• Reason: The location is nearby
beach or services are better than
the rest location.
Average Price Prefer
by People
• On the basis of room type
the average price preferred by
customer for Entire Room is 160.
• For Private Room is 70
• Shared Room is 45
Types of Properties
by Customer Preferences
• There are three types of rooms – Entire
Home/Apartment, Private Room & Shared
Room
• Overall customers appear to prefer
Entire Home (51-85%) & Private Room
(46.26%) in comparison to the shared
room (1.89%).
• Airbnb can focus on promoting shared
rooms with discount offers to increase
booking of a shared room with discounts.
Most Popular
Localities and
Properties in New York
• According to this map more the
darker side represents the most
popular localities and the lighter
side represents the least
popular.
• We can conclude that
Manhattan, Brooklyn & Queens
are much popular than Bronx
and Staten Island.
Top 10 Unpopular
Properties
• Top 10 unpopular locations
where people do not opt for stay.
• Because the location of all
unpopular localities is at the corner
of the city where people do not
wish to visit or there may not be
any tourist attraction point
Adjustments in the existing properties
to make it more customer-oriented
• With the exception of Manhattan and Brooklyn, every other city needs to alter
its marketing plan to boost sales.
• Most customers prefer to invest their money in the $40 to $160 range. Try a
fresh marketing tactic to draw customers, such as offering deals and
reductions.
• Every unpopular locality needs to alter their current plan in order to increase
revenue, such as by creating a tourism draw.
• Increase the customer's purchasing ability, etc.
• Bookings from clients may rise if there are more coastal purchases and new
construction.
Recommendation
• Promotion of shared accommodations with focused savings to boost reservations.
• As long as the new acquisition or growth meets the criteria for both customer traffic
volume and customer happiness, it can be done for between $40 and $160.
• As long as they fall within the desirable price range ($40-$160), new purchases can be
looked into to purchase "private rooms" in Manhattan and Brooklyn and "entire homes"
in the Bronx and Queens.
• Brooklyn costs $113 on average. Given the abundance of listings in Manhattan, Brooklyn
may be regarded for growth.
• Bookings from clients may rise if there are more coastal purchases and new construction.
• Focus on prime locations like Manhattan and Brooklyn where people show interest.
Thank You
