More talks in the program:
Hotel cancellations can cause issues for many businesses in the industry. Not only do cancellations result in lost revenue, but this can also cause difficulty in coordinating bookings and adjusting revenue management practices.
This session explores how machine learning techniques can be used to predict hotel cancellations. Firstly, data manipulation techniques with pandas are employed to effectively process over 20,000 customer entries. Then, feature selection tools such as the Extra Trees Classifier are used to pinpoint the main drivers of hotel cancellations. The use of logistic regressions, support vector machines, and SARIMA are employed for prediction purposes, and extensive visualizations with pyplot are also generated to illustrate cancellation trends across different time periods.