The activeness of regional business entities, like restaurants, cinemas and shopping malls, represents the evolvement of their corresponding commercial districts, whose prediction helps practitioners grasp the trend of commercial development and provides support for urban layout. On the other hand, online social network services, such as Yelp, are generating massive online reviews toward business entities every day, which provide a solid data source for the prediction of regional commercial activeness and entity condition through big data technology rather than applying business data with limited access and poor time efficiency. Inspired by the outstanding performance of deep learning in the field of image and video processing, this paper proposes a deep spatio-temporal residual network (DSTRN) model for regional commercial activeness prediction using online reviews and check-in records of commercial entities. Furthermore, aiming at predicting business trend of entities, we also propose a novel multi-view entity condition prediction model (SBCE) based on online views, along with business attributes and regional commercial activeness. The experiments on the public Yelp datasets demonstrate that both DSTRN and SBCE outperform the compared approaches.

中文翻译：

---

基于在线评论的区域商业活跃度和实体状况预测

餐厅、电影院、商场等区域商业主体的活跃度，代表了其对应商圈的演进，其预测有助于从业者把握商业发展趋势，为城市布局提供支撑。另一方面，Yelp等在线社交网络服务每天都在对商家实体产生海量在线评论，为通过大数据技术预测区域商业活跃度和实体状况提供了坚实的数据源，而不是应用商业数据。访问受限，时间效率低下。受到深度学习在图像和视频处理领域的出色表现的启发，本文提出了一种基于商业实体在线评论和签到记录的区域商业活跃度预测的深度时空残差网络（DSTRN）模型。此外，针对实体的商业趋势预测，我们还提出了一种新颖的基于在线视图、商业属性和区域商业活跃度的多视图实体状态预测模型（SBCE）。公共 Yelp 数据集上的实验表明，DSTRN 和 SBCE 都优于比较方法。