The probability of 90.94% of customer are likely to cancel their hotel bookings because they have a history of prior cancellations.

The probability of 91.63% (6,483 instances; 5.44% of data) of customers are also likely to cancel because they have had previous cancellations, even outside of the summer months, at a City Hotel with children. Overall, customers with a history of prior cancellations are most likely to cancel their hotel bookings.

The probability of 61.42% of customers are not likely to cancel because they do not have prior cancellations, during the summer months, at a City Hotel with no children.

A) Explain how you can use the concepts of entropy and information gain to determine which attributes in this data set are the most informative attributes and how this information can be used to build a classification decision tree.

B) Using the prediction information mentioned above from the tree induction model, explain the probability of which customers are most likely to cancel their hotel bookings.

Report the key findings of your analysis and who seems to be the most likely to cancel a reservation. This should include:

A discussion of at least one probability taken from a leaf node on the decision tree and its decision-making importance.

How the hotel chain can use this decision tree to improve their business decision making.

The limits of the results of this analysis when considering the use of the model.