Booking cancellations often directly impact a hotel's bottom line: many times the room(s) reserved are not booked again, resulting in lower occupation and, subsequently, revenue. To hedge this risk, hotels often demand a booking deposit, often calculated as a percentage of the reservations full price. However, this practice can directly impact demand as some customers might look for different hotels with no deposit (or a smaller one). Our goal is to build a model that, by predicting whether a booking will be cancelled or not, can be used by the hotel to implement different risk-aware strategies for calculating the deposit size. 

Let's use our recently acquired ML skillset to build a classifier! In this case we've been asked to create a model predicting booking cancellations in 2 different hotels. The data utilized here is real world anonymized data.

Data source:  https://www.sciencedirect.com/science/article/pii/S2352340918315191