Discover the Best Airbnb Listings: An Interactive Data Analysis Tool

About Data

the dataset we used for this project was called "Airbnb Listings & Reviews" and was obtained from the Maven Analytics website. This dataset was sourced from Inside Airbnb.

The dataset contained information on more than 200,000 Airbnb listings in 10 different cities, including the host's superhost status, the city and neighborhood of the listing, the type of property, room type, listing price per night, review score rating, and listed amenities.

The data provided a comprehensive overview of Airbnb listings in different cities and allowed us to identify patterns and trends in the data. By analyzing the data, we were able to gain insights into the most expensive cities, the types of listings that were most popular, and the amenities that were most commonly listed.

Project Description

Airbnb Listings Data Analysis is an interactive data analysis project designed to help users make more informed decisions when choosing an Airbnb listing. The project provides a visual overview of Airbnb listings in 10 different cities, including information about the city, neighborhood, property type, room type, price, review score rating, and listed amenities provided by the host.

To analyze and visualize the data, we used Python for exploratory data analysis (EDA) and Tableau for building an interactive dashboard that allows users to filter listings based on their needs. For data processing and preparation, we created several calculated fields, including Price in Dollar and Negative Sentiment, to help users evaluate the listings more effectively.

Our dashboard allows users to filter listings by price range, room type, and host type, making it easy to find the perfect Airbnb listing in Sydney or any of the other cities in our dataset. With its comprehensive data analysis, interactive dashboard, and unique insights into the cities and neighborhoods featured in the dataset, the Airbnb Listings Data Analysis project provides a powerful tool for anyone looking to book an Airbnb listing.

Analytics Approach

The Airbnb Listings Data Analysis project involved several steps to process, analyze, and visualize the data. First, we downloaded the dataset from the Maven Analytics website and imported it into Python for exploratory data analysis (EDA). During the EDA phase, we used Python to examine the structure and quality of the data, looking for any inconsistencies, missing values, or potential outliers.

Here is a brief step-by-step description of the analytical approach we used:

• Dealing with missing data

• Calculated fields: We created several calculated fields to prepare the data for analysis. One example is converting the price of listings from local currency to USD.

• Negative sentiment: We analyzed the "review scores" variable to evaluate which city had the lowest review scores.

• Splitting data: We split the "Amenities" variable into multiple fields to enable better analysis.

• Pivot data: We used Tableau's pivot feature to calculate new information based on in-field data, such as amenities and reviews.

These steps allowed us to analyze the data and create an interactive dashboard that provides useful insights to users looking for Airbnb listings.

In addition to the dashboard, we used Tableau to create several other charts and visualizations that highlight different aspects of the data. For example, we created a chart that shows the relationship between Price and Review Scores across different cities, allowing users to see which cities offer the best value for their money. We also created a chart that compares the number of listings in each city with the average review score, providing insight into how popular cities compare in terms of overall satisfaction.

Overall, our analytical approach involved a combination of Python for data processing and exploratory analysis, and Tableau for visualization and dashboard creation. By leveraging these tools and techniques, we were able to provide a comprehensive and interactive analysis of the Airbnb Listings dataset that helps users make more informed decisions when choosing an Airbnb listing.

Results

Dashboard

Our interactive dashboard allows you to filter based on city, price per night range, room type, and host type, making it easy to find the ideal Airbnb for your needs. This dashboard also provides interesting insights into the data, such as:

• • The fact that Sydney is the most expensive city in our dataset, followed closely by Cape Town. 

  • Paris has the most listings and the most negative review scores. 

  • Super-hosts, in general, have lower prices, except for Paris. 

Our dashboard provides a wealth of information and is an essential tool for anyone planning an Airbnb stay.

Feel free to explore the interactive dashboard further here by adjusting the filters or experimenting with different charts and visualizations. The possibilities are endless!

The Story of Sydney

Why Sydney?! One interesting finding from our analysis is that Sydney is the priciest city in our dataset and on average is about 5 times more expensive than Istanbul which is on the bottom of the list. With about 11% of the no. of the listings, Sydney includes 38 neighbourhoods and 89 property types. So, we decided to explore Sydney in more detail and find out what makes it so expensive. Through our exploration of neighbourhoods, property types, and amenities, we hope we were able to provide insights into what makes Sydney such an expensive and desirable location.

If you want you can explore more here.

We hope you enjoyed exploring our data story and interactive dashboard about the Airbnb listings in Sydney. But don't let it stop here! There is still so much more to uncover in the data.

The full report of this project can be found on my GitHub and Here is the presentation file specifically created for this project.

Project Credits

This project was created by [Maryam Aliakbari], with contributions from [Farzin Valiloo] and [Harold Espinosa].

Maryam were responsible for designing the project, conducting the data analysis, and creating the interactive dashboard. She utilized Python for exploratory data analysis and Tableau for creating the dashboard.

Farzin and Harold provided valuable feedback and suggestions throughout the project, helping to refine the analysis and improve the final results.

Together, the team worked collaboratively to create a compelling and informative data analysis project that showcases the power of data visualization and storytelling.