Article Preview
TopIntroduction
Today, as the social economy thrives and living standards soar, tourism has evolved into a thriving industry and a preferred leisure pursuit for many. Against the backdrop of a global push toward a well-rounded, prosperous society, the tourism sector is undergoing a transformative era characterized by rapid innovation and development. A prime example of this transformation is China’s strategic One Belt, One Road (now known as Belt and Road) initiative, which has significantly accelerated tourism growth in participating countries and cities. Moreover, the swift expansion and modernization of transportation infrastructure—particularly high-speed rail networks—have dramatically reduced travel time and costs, facilitating increased international and domestic mobility.
Amid this surge in tourism activity, however, lies a complex challenge for stakeholders: effectively managing the dynamic and often unpredictable nature of visitor flows. Seasonal fluctuations, special events, and emerging trends can lead to surges or lulls in tourist numbers, presenting both opportunities and challenges for destinations. Overcrowding, underutilized resources, and environmental strain are just a few of the consequences that can arise when visitor flows are not accurately anticipated and managed (Guizzardi et al., 2021).
To address these challenges, the tourism industry increasingly turns to innovative solutions, such as smart tourism, which harnesses big data technology to optimize operations, enhance visitor experiences, and promote sustainable practices. At the heart of smart tourism lies the ability to predict and analyze tourist traffic patterns with precision, enabling informed decision-making and strategic planning (Ma, 2024). Despite advancements in data-driven approaches, however, a pressing need remains for more accurate, real-time forecasting tools that can effectively respond to the ever-changing landscape of tourism demand.
In this study, therefore, I endeavor to explore the forecasting effect of smart tourism passenger flow supported by big data technology, with the ultimate goal of enhancing the intelligence of smart tourism management. By focusing on the temporal variations in tourist traffic, specifically utilizing the tourist traffic data in Xi'an from May 1, 2020, to April 1, 2021, as a sample period, I aim to construct a robust, accurate prediction model using the autoregressive integrated moving average (ARIMA). This widely recognized statistical technique is employed to build a smart model for tourism passenger flow predictions, which will then be rigorously evaluated and analyzed.
The primary objective of this research is to demonstrate the efficacy of the ARIMA model in accurately predicting and analyzing smart tourism passenger flows, providing a valuable reference for subsequent tourist management and the intelligent development of scenic spots. By doing so, I hope to contribute to the ongoing advancement of the tourism industry by offering a powerful tool that can help stakeholders navigate the intricate demands of visitor flow management in an increasingly interconnected and data-driven world.