DublinBnB

Inspiration

Created to tackle the stratascratch "Market Analysis in Dublin" data challenge

What it does

We used the given data from searches and contacts of Airbnbs in Dublin to create a random forest machine learning model that can recognize when people are most likely to book a listing.

How we built it

Data Management: MySQL database
Data Manipulation and Analysis: pandas, sklearn
Data Visualization: plotly

Challenges we ran into

We all had different experience levels in data visualizations and analysis coming into the datathon. Learning how to use different plotting libraries to fulfill our ideas was an uphill battle.

Accomplishments that we're proud of

We're proud that we were able to draw conclusions from the data and produce a high-accuracy random forest model.

What we learned

We learned how to analyze a dataset for use in machine learning and pre-process the data to make the ingest easier. We also learned how to create a story with data to convey all of our research!