Dynamic evaluation method of regional cultural tourism digital platform performance based on multivariate data envelopment analysis and control feedback mechanism

Our research is mainly aimed at a problem that many places often have when evaluating the performance of cultural and tourism digital platforms - that is, the evaluation method is static and lacks a dynamic feedback mechanism. This kind of static analysis is difficult to reflect the changes in platform operations in real time, and it is difficult to provide effective intervention suggestions. Therefore, this time we proposed a new dynamic performance evaluation method, which combines multivariate data envelopment analysis, that is, DEA model, with a control feedback mechanism. The core of this method is: we use a sliding time window to construct a multivariate DEA model, and then embed a feedback control strategy, so that the platform efficiency can be monitored in time series, and the strategy can be adjusted dynamically. We also conducted a simulation experiment, selecting three representative regional cultural and tourism platforms, based on a multi-period, multi-indicator data set, to compare the performance of our new model with the traditional static DEA method. The experimental results are quite interesting. The efficiency of the three platforms has been significantly improved. The average efficiency of platforms A, B, and C has increased by 18.7%, 12.5%, and 15.3%, respectively. These results show that our method has strong adaptability and practicality when facing complex systems that require dynamic evaluation. This study also expanded the application boundaries of DEA in the field of digital public governance, constructed a performance evaluation framework with closed-loop regulation capabilities, and provided a quantifiable strategy optimization tool for local governments and platform operators.