Spatiotemporal prediction of foot traffic
Spatiotemporal prediction of foot traffic
复制标题
DOI：
10.1145/3486183.3490997
复制
发表时间：
2021-11
期刊：
影响因子：
--
通讯作者：
Samiul Islam;Dhruv Gandhi;Justin Elarde;T. Anderson;A. Roess;Timothy F. Leslie;H. Kavak;Andreas Z
中科院分区：
文献类型：
--
作者：
Samiul Islam;Dhruv Gandhi;Justin Elarde;T. Anderson;A. Roess;Timothy F. Leslie;H. Kavak;Andreas Z
客流量是一个商业术语，用来描述进入兴趣点（POI）的客户数量。这项工作旨在预测未来的人流量：来自每个人口普查块组（CBG）的人数将访问研究地区的每个POI，并具有潜在的营销和广告应用。现有的人流量时空预测技术使用基于位置的社交网络数据，这些数据存在稀疏性，每天只能捕获少量的访问量。这项研究利用了来自SafeGraph的高度细化的人流量数据，SafeGraph是一家数据公司，仅在美国就收集了每天数亿人次的移动数据。利用这些数据，我们探索了在POI水平上预测每周人流量数据的解决方案。我们提出了一种基于（POIs x CBGs x Weeks）数据张量的张量分解协同过滤方法。这种方法为我们提供了前几周所有POI-CBG对访问的去噪估计。使用这个张量，我们探索了各种时间序列预测模型：周滚动平均、加权周滚动平均、单变量线性回归、多项式回归和长短期记忆（LSTM）递归神经网络。我们的研究结果表明，在所有的预测模型中，协同过滤步骤一致地提高了预测结果。我们还发现，简单加权平均法始终比更复杂的方法表现得更好。鉴于如此丰富的人流量数据，该结果表明我们可以通过利用协同过滤来改善人流量数据的时空预测。
Foot traffic is a business term to describe the number of customers that enter a point of interest (POI). This work aims to predict future foot traffic: the number of people from each census block group (CBG) that will visit each POI of a study region with potential applications in marketing and advertising. Existing techniques for spatiotemporal prediction of foot traffic use location-based social network data that suffer from sparsity, capturing only a handful of visits per day. This study utilizes highly granular foot traffic data from SafeGraph, a data company that collects mobility data regarding hundreds of millions of visits per day in the United States alone. Using this data, we explore solutions to predict weekly foot traffic data at the POI level. We propose a collaborative filtering approach using tensor factorization on the (POIs x CBGs x Weeks) data tensor. This approach provides us with a de-noised estimation of visits in previous weeks for all POI-CBG pairs. Using this tensor, we explore various time series prediction models: weekly rolling average, weighted weekly rolling average, univariate linear regression, polynomial regression, and long short-term memory (LSTM) recurrent neural networks. Our results show that of all the prediction models, the collaborative filtering step consistently improves prediction results. We also found that a simple weighted average consistently performed better than the more sophisticated approaches. Given this abundance of foot traffic data, this result shows that we can improve the spatiotemporal prediction of foot traffic data by harnessing collaborative filtering.