Skip to content

Niez-Gharbi/Airbnb_price_prediction

Repository files navigation

RAMP starting kit on AirBnB price prediction

Authors: Mohamed Badreddine Dammak, Syrine Cheriaa, Salma Salhi, Niez Gharbi

Airbnb is an online marketplace for arranging or offering lodging, primarily homestays, or tourism experiences. It emerged as a web platform where users can rent out their space to host travelers to save money while traveling, make money when hosting and share culture through local connection to the city.

The Airbnb website allows customers to search by city, review listings and book a place. The platform uses a commission revenue model as the primary source of revenue. Both hosts and travellers have to pay a service fee from bookings.

Airbnb is famous for its extensive functionality that is equally convenient for travellers and property owners and has become a giant in rental business. There are a lot of factors that make Airbnb an outstanding example of a successful rental marketplace. The right business model and diverse functionality are among them.

The predictive aim of this problem is to use the diverse features that we will extract from the datasets in order to predict the prices of the different housings and lodgings listed by Airbnb. This allows to improve the experience of the customers and helps the hosts to set the price for their properties in order to increase their income.

Set up

Open a terminal and

  1. install the ramp-workflow library (if not already done)
$ pip install git+https://github.com/paris-saclay-cds/ramp-workflow.git
  1. Follow the ramp-kits instructions from the wiki

Local notebook

Get started on this RAMP with this notebook.

To test the starting-kit, run

ramp_test_submission --submission starting_kit

or for a test mode :

ramp_test_submission --submission starting_kit --quick-test

Help

Go to the ramp-workflow wiki for more help on the RAMP ecosystem.

About

AirBnB price prediction RAMP starting kit

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published