A hybrid deep learning model for tourism trend forecasting based on big data and spatiotemporal pattern analysis

With the rapid development of information technology (IT), trend prediction based on big data has become a research hotspot. With the increasing popularity of big data technology, the tourism industry has accumulated massive amounts of data. These data provide a foundation for scientific prediction of tourist flow. Accurately and timely predicting tourist flow can not only optimize the travel experience of tourists, but also provide important support for the sustainable development of the tourism industry. The prediction of tourist flow can provide key basis for tourism planning and development, policy formulation, etc., help alleviate market contradictions, promote the rational allocation and efficient utilization of tourism resources, and thus promote the coordinated development of the tourism industry. This article proposes a tourism market trend prediction model based on big data analysis. This model combines deep learning (DL) algorithms to accurately predict tourist flow. The results show that our model performs excellently in terms of prediction accuracy and performance, and can effectively capture the dynamic trends of the tourism market. This research achievement not only provides scientific decision-making support for tourism management departments, but also opens up new paths for the intelligent development of the tourism industry.