Data Asset Value Assessment Using an Enhanced Multi-Period Excess Return Method Based on Time Series Forecasting: A Case Study of Trip.com Group

With the rapid advancement of digitalization and smart technologies, tourism services have transitioned from traditional offline models to dynamic online platforms, integrating resources and offering diverse services such as online booking, itinerary planning, destination recommendations, and user reviews. These platforms leverage data analytics to deliver personalized travel experiences by analyzing user preferences, behavioral patterns, and location information. Such data enables travel platforms to accurately identify market demands, enhance operational efficiency, and improve user satisfaction and loyalty through precise profiling and recommendation systems. As a result, data assets have become critical resources for value creation, service optimization, and competitive advantage in the internet travel industry. Despite their significance, the accurate assessment of data asset value remains a complex challenge, particularly for internet travel platforms. Addressing this issue, this paper systematically reviews existing methods for data asset evaluation, highlights their limitations, and introduces an improved multi-period excess return evaluation framework tailored for the unique needs of internet travel platforms. This framework incorporates time series forecasting to predict future financial metrics and employs the entropy-weighted analytic hierarchy process (AHP) to quantify the contributions of off-balance-sheet intangible assets. Using Trip.com Group as a case study, the paper validates the framework by calculating the platform's data asset value and demonstrating its applicability and reliability. The findings provide theoretical insights and practical tools for assessing data assets, offering significant guidance for both academia and industry in the era of data-driven tourism services.