Research on Optimization Algorithm for Abnormal Detection of Passenger Transfer Efficiency on Airport Big Data Platform

This paper proposes an optimization algorithm based on big data platform to detect abnormalities in passenger transfer efficiency, and optimizes it through data mining and machine learning technology to improve detection accuracy and response speed. The study first defines the relevant indicators of passenger transfer efficiency and conducts an indepth analysis of the factors affecting efficiency. Secondly, an optimization algorithm framework that comprehensively uses cluster analysis, regression analysis and anomaly detection algorithms (such as isolation forest and support vector machine) is designed to achieve real-time detection of transfer efficiency anomalies. The experiment results show that the proposed algorithm can increase the precision of the algorithm by 30%, the false alarm rate is decreased to 5%, and the processing speed is about 70% higher than the conventional method. The experiment also shows that the optimization algorithm can effectively cope with large-scale data sets, identify potential transfer bottlenecks, and maintain good adaptability in different airport operating environments. This study provides efficient technical support for airport management and lays the foundation for subsequent intelligent management systems.