Airbnb has become increasingly popular among travelers for accommodation across the world. In this project, we aim to predict Airbnb listing price, to find the spike in accommodation price during peak and off-peak seasons and to find the review score with the help of sentimental analysis in four different cities- Boston, Amsterdam, Hong Kong and Athens with various machine learning approaches. After doing price prediction using various ML algorithms it was noticed that Random Forest and Naive Bayes Classification algorithm give the highest accuracy when compared with actual price. After finding the review score and doing sentimental analysis of all the cities we can say that the Airbnb reviews are almost similar across different cities. Most tourists leave positive reviews and use similar positive words to describe the Airbnb houses. After determining that the peak season for these cities is October, with the exception of Hong Kong, which has a busiest time in April. In addition, there is a significant price difference between off-season and peak-season hotel rates.
- To predict and validate the price of different cities of different continents and compared it to recommend the best according to the need of Airbnb users and non-users.
- To apply sentimental analysis on Airbnb dataset of different cities.
- To predict the spike in accommodation prices during peak and off-peak seasons of different cities.
We have used the dataset of Boston, Amsterdam, Hong Kong and Athens from the official site of Airbnb i.e., http://insideairbnb.com/get-the-data.html
HAPPY LEARNING!! ✌😇