Foot traffic data for finance by Passby

pass_by's foot_traffic for finance enables Financial Institutions to accurately measure and predict store performance for over a million retail locations across the US. From predictive insights on how much foot traffic a publicly traded retailer will have in the next quarter, to macro analysis on a national brand’s consumers, you can get the data you need to drive your decision-making. Using location data as a base, pass_by’s foot_traffic for finance combines multiple data sources, including ground truth validation from in-store sensors, to not only measure the most accurate footfall data in the market but to predict it 90 days into the future. Using our data feeds, it’s never been easier to enhance your investment models with ground truth-validated retail data.

***Why pass_by?***

1. **Ground truth validated**: Our store visits data is trained and validated against in-store foot traffic counters, enabling a correlation accuracy of up to 0.91.
2. **Largest sample panel**: The location data of over 177 million daily US mobile devices are analyzed to power our analytics.
3. **Representative panel**: This panel of devices closely matches the US national average on age, income, race, and more, making them a representative sample of the population.
4. **Proprietary AI models**: From clean data to attributing store visits, to producing predictive insights - our AI models are the key to the quality of our datasets.
5. **Comprehensive network of datasets**: As well as location data, these models are powered by census data, Safegraph’s point-of-interest data, Transunion’s consumer data, and more.
6. **Normalized and Scaled**: pass_by’s data is scaled to represent the full population, and normalized so as to provide a consistent view of footfall over time.

***The Product***

-  Foot traffic data for the financial industry. Covering 6,677 brands 1,065 publicly traded)
- Mapped to 484 tickers
- Data starting January 2019
- Point in Time (PIT) starting from March 2022
- 90-day predictive foot counts, with a median 90% correlation to our historical foot traffic

pass_by面向金融行业的客流（foot_traffic）解决方案可助力金融机构精准测算并预测全美超100万家零售门店的运营表现。从预测上市零售商下一季度的客流规模，到对全国性品牌的消费者开展宏观分析，您均可获取助力科学决策的精准数据。本方案以位置数据为基础，整合多源数据（包括门店传感器生成的实地验证（ground truth validation）数据），不仅可测算出市场中精度最高的客流数据，还可实现未来90天的客流预测。通过我们的数据接口，您可轻松借助经实地验证的零售数据优化投资模型。

***为何选择pass_by？***
1. **实地验证（ground truth validated）**：我们的门店到访数据依托门店客流计数器进行训练与验证，相关关联精度最高可达0.91。
2. **超大规模样本面板**：我们的分析基于全美超1.77亿台每日活跃移动设备的位置数据构建。
3. **具有代表性的样本面板**：该设备样本在年龄、收入、种族等维度与美国全国平均水平高度契合，可精准代表全体人群特征。
4. **专属AI模型**：从数据清洗、门店到访归因到生成预测洞察，我们的AI模型是保障数据集质量的核心。
5. **多源数据集网络**：除位置数据外，本模型还整合了人口普查数据、Safegraph的兴趣点数据、Transunion的消费者数据等多类数据源。
6. **标准化与规模化处理**：pass_by的客流数据经过规模化校准以覆盖全人群，并完成标准化处理，从而实现跨时段客流观测的一致性。

***产品概况***
- 金融行业客流数据，覆盖6677个品牌（其中1065个为上市品牌）
- 可映射至484个股票代码
- 数据起始于2019年1月
- 时点（Point in Time, PIT）数据自2022年3月起提供
- 提供90天客流预测数据，其与历史客流数据的中位关联精度达90%

原始信息汇总

数据集概述

标题

pass_by: Foot traffic data for finance by Passby

图标

• 16x16像素的PNG图标
• 32x32像素的PNG图标
• 48x48像素的PNG图标
• 96x96像素的PNG图标
• 144x144像素的PNG图标

搜集汇总

背景与挑战

背景概述

该数据集为金融机构提供全美超百万零售点的精准客流量监测与90天预测数据，融合门店传感器等多源信息验证，覆盖6677个品牌（含1065家上市公司）。其特色包括0.91的高精度验证、1.77亿移动设备定位分析以及标准化的人口代表性数据。