Cost-based Attraction Recommendation For Tour Operators Under Stochastic Demand

Over the past decades,tourism has experienced continued expansion,becoming one of the largest and fastest growing economic sectors in the world.In China,tourism has become an important pillar industry.With the rapid development of tourism industry,the number of tour operators has been increasing rapidly,and the tour operators are confronting fierce competition.To survive in today's competitive market and expand market share,accurately identifying the tourists' preferences and consequently presenting customized travel products and services are crucial to the tour operators.Attraction recommendation is a key functionality offered by tour operators.The main stakeholders of attraction recommendations include tourists who refer to the recommendation to make traveling decisions and the tour operator who operates the recommendation for its own benefit.Most existing attraction recommendation methods focus on providing recommendations that best match the tourists' preferences,yet overlook the benefit that attraction recommendation could bring to the tour operator.In reality,customer satisfaction is not the only concern to the tour operators,cost control is also crucial.To address this gap,we conduct a study focused on cost-based attraction recommendation under stochastic tourist demand from the perspective of tour operators.This thesis contributes the following contents:1.We investige the state--of-the-art researches of travel recommendation and cost/profit-based recommendation,based on which we indicate the shortcomings of present works and the importance of our work;2.We analyze the main cost categories of attraction recommendation of the tour operator and the impact of stochastic tourist demand,and formulate the cost-based attraction recommendation problem;3.We then propose a two-stage stochastic optimization model that involves joint chance constraint to optimize the traditional attraction recommendation solution,and further present a solving algorithm based upon Sample Average Approximation(S AA)method;4.Finally,comprehensive experimental studies are conducted with simulated instances as well as a real-world case to verify the effectiveness of the proposed cost-based attraction recommendation method.