With the increasing popularity of Location-Based Social Networks (LBSNs), a significant volume of check-in data of users has been generated. Such massive data brings difficulties for the users to efficiently retrieve their desired point-of-interest (POI). As a result, POI recommendation systems have received extensive attention from academia and industry. Currently, most existing POI recommendation approaches only provide users with a fixed set of recommended POIs based on the historical check-in records of the users, and cannot achieve flexible and feasible recommendations according to different spatial and temporal situations of the users. In this paper, we propose a next POI recommendation model that will predict POIs to be visited by users in the next few hours according to their historical check-in data and current contextual information (such as the current time and locations of the users). In our model, we propose a unified approach to calculate context-aware similarities between different users by investigating the influences of both temporal and spatial features for the users. We also propose an approach to dynamically generate different POI recommendation lists for a particular user according to different current context information of the user. Compared with the state-of-the-art POI recommendation approaches, the experimental results demonstrate that our system achieves much better performance.

Margin distribution has been proven to play a crucial role in improving generalization ability. In recent studies, many methods are designed using large margin distribution machine (LDM), which combines margin distribution with support vector machine (SVM), such that a better performance can be achieved. However, these methods are usually proposed based on single-view data and ignore the connection between different views. In this article, we propose a new multiview margin distribution model, called MVLDM, which constructs both multiview margin mean and variance. Besides, a framework is proposed to achieve multiview learning (MVL). MVLDM provides a new way to explore the utilization of complementary information in MVL from the perspective of margin distribution and satisfies both the consistency principle and the complementarity principle. In the theoretical analysis, we used Rademacher complexity theory to analyze the consistency error bound and generalization error bound of the MVLDM. In the experiments, we constructed a new performance metric, the view consistency rate (VCR), for the characteristics of multiview data. The effectiveness of MVLDM was evaluated using both VCR and other traditional performance metrics. The experimental results show that MVLDM is superior to other benchmark methods.

Recently, many deep learning-based models have been successfully applied to click-through rate prediction. However, most previous models focus only on feature-level interactions between a single user behavior and the target item or only treat the user’s historical behavior as a sequence to uncover the hidden interests behind it when mining user interests. This can lead to user interest that evolves over time dynamically being ignored or the interest shown by a single user’s behavior not being exploited. Based on the above problems, we propose evolving interest with feature co-action network (EIFCN). Specifically, we first design user dynamic interest network to treat the user’s historical behavior as a sequence of information, and tap into the user’s hidden interests over time. In this part, we use a multi-head self-attention mechanism to initially process the data and then pass it into the deep learning network. Then a feature co-action network is designed to mine the user’s single behavior and the displayed feature-level interactions of the target item. Experimental results show that the EIFCN model performs better than other models.