Airbnb pricing recommendation

• 

  Conceptual diagram

• 

  Data analysis RDD flow

Inspiration

As a current AirBnb service provider, one of the biggest business pains is determining the optimal pricing strategy for my properties. Therefore, I took this opportunity to develop a solution that would help me make the right decisions and maximize my rental revenue.

What it does

It take the current listing and availability information provided by AirBnb and determines potential revenue opportunities for properties based on regional characteristics.

How we built it

1. Read the most recent listing and schedule information from csv files provided by AirBnb.
2. Imported the data and filter out unnecessary columns.
3. Group listings by proximity, property type and room type.
4. Conduct pricing analysis based on availability and current/upcoming events.
5. Dynamically store the calculated metrics for future use by the application.

Challenges we ran into

Initially, a focus of this application was to discover potential nearby Points-Of-Interests based on listing information. However, we discovered that the development of this feature was more challenging that initially expected and would require a significant effort to effectively implement.

Accomplishments that we're proud of

This project allowed us to discover the capability of Spark's in-memory processing. We will use this experience to potentially utilize Spark for future business applications.

What we learned

As a result of this initiative, we were able to discover potential trends in regional rental supply. In addition, we assessed the capacity of Spark's in-memory computational capacity and are interested in applying this to real time data.

What's next for Air BnB Pricing Recommendation

We are still in the process of developing this application.

Built With

• java
• particle
• scala