Determining Theme Park Attraction Attributes: An Analysis of Factors that Impact Theme Park Attraction Popularity and Success

Theme parks have some attractions that are more popular than others, referred to as main ticket attractions (MTA). The purpose of this thesis is to create a model which can successfully predict whether or not theme park attractions are considered MTA. Data from leading USA theme park attractions has been recorded and analyzed for this thesis. A neural network model has been created using Matlab that categorizes attractions with up to 85% accuracy. However, some of the inputs are considered unstable once run through SAS JMP. To create a comparative study, a decision tree has been created in Matlab with the same 15 inputs. Five attractions were withheld from the models to compare their results. In the end, the decision tree categorized 90% of the attractions correctly, while the neural network categorized 80% appropriately