We report results using n-grams to model user actions with only aggregated data and knowing little about the user. Employing a data set of 33,860 flight bookings from 4,221 passengers, we evaluate the n-gram model for the precision of predicting next likely actions. Results show that our approach can achieve a precision of 21% overall and 88% for some user behavior patterns, which is well above a baseline of 11.8% of recommending the most popular destinations. We achieve this performance with minimal complexity by using a first-order model of two states. However, the coverage is limited to about 21% of the destinations. Implications are that the n-gram approach can predict short customer behavior patterns when individual customer information is not available for specific sequences of actions. The findings have consequences for understanding customer populations for tasks that can be state modeled within the airline domain and similar contexts. Findings may also apply to other user-facing tasks, such as predicting website transitions or next likely clicks.