Madrid Airbnb: What are affordable neighbourhoods for rentals?
Introduction
It is clear that affordable rentals play an essential role in planning for the trip and to experience the real-life of the city for travellers. In this article, we will explore the Madrid Airbnb dataset and answer several questions like:
- What is the Average daily price per neighbourhood wise along with ratings?
- What are the frequent amenities in Madrid?
- What are the most important features that contribute to Airbnb price?
Let's starts with an overview of the dataset...
The original dataset consists of 19618 listings. With the category of rental distribution as
Madrid hosts list most in-home/apartments categories from the above table with 57.67 per cent of the total share. In comparison, the private room takes a share of 40 per cent and remaining with shared rooms and hotel rooms.
The following graph helps diving into the distribution of the listings around the cities with total numbers indicates within the neighbourhood.
Madrid listing’s price distribution indicates that most listings are between 0 and 400 dollars, with 350 as a 95 quantile percentage. So for further preprocessing, listing above 350 are removed, which will help in better accuracy predictions.
Q1: What is the Average daily price neighbourhood wise along with rating?
The above map shows the average price per neighbourhood. It seems to indicate that affordable rental communities are scattered around the city rather than along the outskirts.
To verify by plotting the most affordable neighbourhoods(Top 25 out of 128). We conclude that affordable cities are not just along the city's borders but also in the core regions. The following table shows the most areas along with ratings.
Further, Affordable neighbourhoods are scattered around the cities indicate the influence of the location on the price.
Q2: What are the most frequent amenities in Madrid?
By preprocessing the amenities column from the dataset and plotting the 20 most frequent amenities out of 539 total, We arrive at the following:
As expected, essentials are on the top, followed by wifi. Interestingly, dedicated workspaces and coffee maker supplies as amenities indicate the modern work culture impact on the travel industry.
Q3: What are the most important features that contribute to Airbnb price?
Fitting the dataset using gradient boosting decision trees(Machine Learning Model) and finding the top features contribute to the prediction. We observe that accommodates(Number of visitors) has a significant influence on the price. Then we have the influence of room type as private and entire home as it costs more than remaining types. The influence of location on the price is also clearly indicated from latitude and longitude in top features. As expected, the number of reviews, reviews score rating influences price listings. Interestingly, the review score cleanliness contribution shows the interest of travellers in the cleanliness of the house more than check-in, communication, and location scores.
Conclusion:
In this article, we have explored the most affordable regions of the cities, the most frequent amenities supplied by hosts, and important features from the dataset that influence the house price.
Moving further, we can suggest travellers about affordable regions in cities that would help save the amount and explore the real-life the town can offer.
For technical details please refer to github repository: Link