Understanding travelers' choices using data analytics

Abstract

Travel and tourism industry is one of the largest and growing industries in the world that depends on choices and demands of travellers. The identification of these choices and demands will provide benefits to both service providers in the industry and travellers. The use of data analytics to achieve this has been discussed briefly over the years using different types of data. The findings of these studies were inconclusive due to limitations in the selected data types, features and analysis techniques. This research aims to overcome these limitations by identifying the factors that impact the choices of travellers, establishing a feature framework to identify those choices, finding the feasibility of using time series forecasting to predict travellers’ demand and proposing the use of data analytics in travel insurance. The limitations in previous studies and the unavailability of necessary data for research have increased the importance of using data analytics in travel insurance, an industry within travel and tourism industry. This research achieves its objectives by conducting a study with data from the UK, one of the best performing outbound markets in the world. The data was analysed using data analytics techniques to find the destination and travel mode choices of travellers and two other subgroups, travellers with medical conditions and cruise travellers. The number of outbound trips and the visitors for destinations were forecasted for a year to find the feasibility of using time series forecasting to predict travellers’ demands. The results of the analysis confirm that a traveller’s age, group type they choose to travel under, and their health have an impact on their destination and travel mode choices, and the two choices have an impact on each other. The study finds that time series forecasting is a reliable demand forecasting technique when a large data set is available.