Online dynamic group-buying community analysis based on high frequency time series simulation

Group-buying often fails even when there are satisfactory quantities as not enough consumers join in the required time, which can waste seller, purchaser, and platform operator time resources; therefore, the group buying features require further research. Over a 3 weeks period, around 700 million click-stream records from 1,061,770 users from a stable and continuous time series were allocated to groups of 5 min frequency, and a hybrid neural network model developed to simulate group-buying behavior in four experiments, from which it was found that adding to the cart and adding as a favorite were significant group-buying behavior features, and shopping depth was the main demographic feature, but age was not. Compared with previous ambiguous online consumer feature conclusions on gender, the results revealed that the commodity feature was the main determinant for gender feature significance. The college student feature was found to be a pseudo feature, and should connect with other fixed effects such as low income or education level. This paper is the first to construct an online dynamic group-buying community, which is a new type of social network and could provide a new perspective for social commerce research. A big data neural network-based method for examining group-buying community behavior over time is proposed that can offer novel insights to online vendors for the development of targeted marketing campaigns.