Research on precise product selection optimization strategy of live e-commerce based on AARRR model from the perspective of digital twin

Abstract

With the rapid development of live streaming e-commerce, product selection has become a key determinant of success, and the college student demographic, as an important consumer market, is gradually becoming a significant target for e-commerce platforms. However, despite the enormous market potential of social e-commerce, how to accurately select products remains a pressing issue that needs to be addressed. This paper focuses on college students as the target group, combining the AARRR model with digital twin technology to explore how to enhance the accuracy and market adaptability of product selection in e-commerce live streaming based on the optimization of the AARRR model. The research has found that existing product selection strategies have blind spots in understanding the needs of the target group and market feedback, particularly among college students, where the accuracy of product selection and market adaptability is relatively low. This paper introduces the AARRR model to quantify user behavior pathways and combines digital twin technology to virtually simulate market responses during the product selection process, proposing an optimized product selection plan targeting the college student demographic. The innovative solution combines social media interaction data (such as likes, comments, and shares) with product market performance, not only addressing the limitations of traditional product selection methods but also providing a more precise decision-making pathway for social e-commerce platforms. This research has broad implications for the entire e-commerce industry.