The development of social media supports and broadens the possibility for consumers to participate in social interaction, not to mention that the online and offline social interaction independently designed by the brand have played an important role in enhancing consumers’ purchase intentions. Based on the perspective of social capital, this article explores the influence of brand social interaction (BSI) on users’ purchase intentions. It discusses the role of BSI factors at the online and offline levels on the formation of social capital, as well as the impact of social capital on continued purchase intentions, and proposes a hypothetical model. Our model is empirically tested through survey data collected from 395 member-level users of Midea, a well-known home appliance brand in China. The empirical results show that online interactive support, immersion, and offline brand activities are important antecedents of social capital, and the last two especially significant. In contrast, the influence of online interactive reaction on shared narratives is supportless. In addition, identification and shared narratives significantly affect purchase intention, while the positive impact of social ties has not been endorsed. Finally, the research discusses the theoretical and practical significance of the results, which is a real and effective guide for companies to carry out BSI, thereby improving consumers’ purchase intentions.

This study was focused on Hangzhou in China that are undergoing large‐scale subway construction, and an improved momentum back‐propagation (BP) neural network model was trained. The model can analyze the complex traffic data, evaluate the service quality of bus line, and improve the estimation accuracy and convergence speed. For the same training data set, the convergence time of the BP algorithm with momentum term is reduced by 0.043 secs, the iterative convergence speed is improved by 0.66%, and the estimation accuracy is improved by 26.7% compared with the standard BP algorithm. Under similar conditions, the convergence time is 1.562 secs less than that of the standard BP algorithm, and the convergence speed was 24.1% higher than that of the standard BP algorithm, and the absolute value of the estimated error was less than 1%. Finally, a representative bus line in Hangzhou was used as an example to evaluate the model. The results showed that the improved momentum BP neural network model had a faster convergence speed and higher prediction accuracy of the comprehensive weight of bus line service quality. The prediction results of the model are consistent with the actual survey results, which indicates that the model constructed is reasonable.