In recent years, the global e-commerce landscape has witnessed rapid growth, with sales reaching a new peak in the past year and expected to rise further in the coming years. Amid this e-commerce boom, accurately predicting user purchase behavior has become crucial for commercial success. We introduce a novel framework integrating three innovative approaches to enhance the prediction model's effectiveness. First, we integrate an event-based timestamp encoding within a time-series attention model, effectively capturing the dynamic and temporal aspects of user behavior. This aspect is often neglected in traditional user purchase prediction methods, leading to suboptimal accuracy. Second, we incorporate Graph Neural Networks (GNNs) to analyze user behavior. By modeling users and their actions as nodes and edges within a graph structure, we capture complex relationships and patterns in user behavior more effectively than current models, offering a nuanced and comprehensive analysis. Lastly, our framework transcends traditional learning strategies by implementing advanced meta-learning techniques. This enables the model to autonomously adjust learning parameters, including the learning rate, in response to new and evolving data environments, thereby significantly enhancing its adaptability and learning efficiency. Through extensive experiments on diverse real-world e-commerce datasets, our model demonstrates superior performance, particularly in accuracy and adaptability in large-scale data scenarios. This study not only overcomes the existing challenges in analyzing e-commerce user behavior but also sets a foundation for future exploration in this dynamic field. We believe our contributions provide significant insights and tools for e-commerce platforms to better understand and cater to their users, ultimately driving sales and improving user experiences.
Urban sprawl increasingly affects the ecology of natural populations, including host-microbiota interactions, with observed differences in the gut microbiota between urban and rural hosts. While different mechanisms could explain this pattern, dietary uptake constitutes a likely candidate. To assess the contribution of diet in explaining urban-rural variation in gut microbiota, we performed an aviary experiment in which urban and rural house sparrows were fed with mimics of urban or rural diets. Before the experiment, rural sparrows hosted more diverse gut communities, with a higher relative abundance of Enterococcaceae and Staphylococcaceae and lower abundance of genes involved in xenobiotic degradation and lipid metabolism than their urban counterparts. The experimental diets significantly altered gut microbiota α- and β-diversity and taxonomic composition, with the strongest shifts occurring in individuals exposed to contrasting diets. Overall, diet-induced shifts resembled initial differences between free-ranging urban and rural hosts. Furthermore, rural diet had a positive impact on urban host body mass but only in hosts with the highest initial gut diversity. Overall, our results indicate that diet constitutes an important factor contributing to differences in gut microbiota along the urbanization gradient and provide new insights on possible fitness consequences of a reduced gut diversity in urban settings.
In recent decades major declines in urban house sparrow (Passer domesticus) populations have been observed in north-western European cities, whereas suburban and rural house sparrow populations have remained relatively stable or are recovering from previous declines. Differential exposure to avian pathogens known to cause epidemics in house sparrows may in part explain this spatial pattern of declines. Here we investigate the potential effect of urbanization on the development of a bacterial pathogen reservoir in free-ranging house sparrows. This was achieved by comparing the prevalence of Salmonella enterica subspecies enterica serotype Typhimurium in 364 apparently healthy house sparrows captured in urban, suburban and rural regions across Flanders, Belgium between September 2013 and March 2014. In addition 12 dead birds, received from bird rescue centers, were necropsied. The apparent absence of Salmonella Typhimurium in fecal samples of healthy birds, and the identification of only one house sparrow seropositive for Salmonella spp., suggests that during the winter of 2013-2014 these birds did not represent any considerable Salmonella Typhimurium reservoir in Belgium and thus may be considered naïve hosts, susceptible to clinical infection. This susceptibility is demonstrated by the isolation of two different Salmonella Typhimurium strains from two of the deceased house sparrows: one DT99, typically associated with disease in pigeons, and one DT195, previously associated with a passerine decline. The apparent absence (prevalence: <1.3%) of a reservoir in healthy house sparrows and the association of infection with clinical disease suggests that the impact of Salmonella Typhimurium on house sparrows is largely driven by the risk of exogenous exposure to pathogenic Salmonella Typhimurium strains. However, no inference could be made on a causal relationship between Salmonella infection and the observed house sparrow population declines.