About the Course
Over the course of two weeks, I had the opportunity to come up with an idea to leverage the Foursquare location data to explore or compare neighborhoods or cities of my choice or to come up with a problem where I could use the Foursquare location data to solve the problem. No matter what I've decided to do, I had to make sure to provide sufficient justification of why I thought what I wanted to do or solve was important and why would a client or a group of people be interested in my project.
I've learned about location data and different location data providers, such as Foursquare. I now Know how to make RESTful API calls to the Foursquare API to retrieve data about venues in different neighborhoods around the world. I've also learned how to be creative in situations where data are not readily available by scraping web data and parsing HTML code. By utilizing Python and its libraries to manipulate data, I was able to refine my skills for exploring and analyzing data.
About the Project
Airbnb is a internet marketplace for short-term home and apartment rentals. It allows you to, for example, rent out your home for a week while you’re away, or rent out your empty bedroom. One challenge that Airbnb hosts face is determining the optimal nightly rent price. In many areas, renters are presented with a good selection of listings and can filter by criteria like price, number of bedrooms, room type, and more. Since Airbnb is a market, the amount a host can charge is ultimately tied to market prices.
Although Airbnb provides hosts with general guidance, there are no easy to access methods to determine the best price to rent out a space.
The aim of this project is to propose a data-driven solution, by using machine learning to predict rental price.
One method could be to find a few listings that are similar to the place that will be up for rent, average the listed prices and set our price to this calculated average price. However, with the market being so dynamic, we would probably be looking to update the price regularly and this method can become tedious.
Moreover, this may not be very accurate, as we are not taking into account other important factors that may give us a comparative advantage over other listings around us. This could be property characteristics such as number of rooms, bathrooms and extra services on offer.
For this project, a predictor based on space will be introduced to the model: the property's proximity to certain venues. This will allow the model to put an implicit price on things such as living close to a bar or a supermarket.