Detection of anomalous ticket purchasing behavior for concerts based on machine learning

Abstract

In recent years, there has been a continuous increase in the demand for entertainment activities. With the changing policies related to epidemic prevention and control, consumers ticket demands for various entertainment events, particularly concerts, have seen a significant rise. This has led to the emergence of anomalous ticket purchasing behaviors, including ticket scalping software, bulk purchasing, and fraudulent transactions. Such behaviors not only infringe upon the rights of legitimate audiences but also harm the interests of concert organizers. Therefore, the detection and prevention of anomalous ticket purchasing behaviors for concerts have become essential. This paper focuses on the use of automated systems, robots, or malicious software for ticket purchases, limiting consumers participation in abnormal ticket-buying activities. Combining previous research on railway ticketing systems and real-life experiences, this study selects ticket-purchasing frequency, speed, quantity, seat selection, payment method, IP address changes, and historical ticket-purchasing records as feature values. Different machine learning models are chosen for different feature values to conceptualize the construction of an anomalous ticket purchasing system for concerts. This paper emphasizes the importance of detecting anomalous concert ticket purchasing behavior, provides different machine learning models for various feature values, and lays the foundation for building an overall anomaly detection system. This research serves as a crucial reference for the security and user experience of ticketing systems, aiming to continually improve and upgrade anomaly detection systems to adapt to evolving challenges. The hope is to enhance the ticket-buying experience for future concerts and large-scale events.