.svg)
Verifying In-store Footfall Accuracy Using Sales Performance Results
How huq used Walmart mobility signals to predict quarterly US net sales and validate a footfall-derived demand model.
The Challenge
The objective was to determine whether huq footfall and dwell-time signals could accurately predict Walmart US quarterly net sales. The work had to control for noisy observations, changing panel size, seasonality and lookahead bias before the output could be useful to analysts and investors.
.svg)
Create a demand proxy
Transform store visits and dwell behaviour into a signal that reflected consumer spending.
.svg)
Control data noise
Remove dwell outliers, normalise panel growth and account for weekdays, weekends and holidays.
.svg)
Validate unseen performance
Separate training and testing periods and select parameters without introducing lookahead bias.
The Solution
huq provided a live behavioural intelligence layer that unified movement trends, catchment visibility, and district benchmarking into a single platform.
.svg)
Movement Intelligence
Live visibility into visitor activity and engagement patterns.
.svg)
Demand Forecasting
Turn mobility and location signals into timely estimates of customer demand.
.svg)
Data Validation & Research
Validate mobility evidence and apply it in robust academic, commercial or policy research.
District Benchmarking
Compare commercial performance across multiple urban environments.
huq used Walmart mobility signals to predict quarterly US net sales and validate a footfall-derived demand model.
huq matched enriched Walmart store-visit data with the Walmart US net-sales segment. Dwell observations were grouped into visits, filtered for outliers and converted into a normalised demand signal that respected panel growth and seasonality.
Case study highlights
- Structured validation: Seventeen quarters were divided chronologically into 12 training and five test periods.
- Signal engineering: Visit duration, dwell thresholds and normalisation rules captured behavioural nuance.
- Large-scale parameter search: More than 750,000 candidate signal combinations were evaluated.
- Independent test: Non-negative least-squares regression was assessed against previously unseen net-sales results.
The selected mobility signal closely tracked reported sales, demonstrating how location evidence can support high-frequency demand research.
Results & Operational Impact
With huq first clients achieve significantly stronger visibility into commercial demand, engagement growth, and estate performance.
.avif)
Faster leasing evaluations
Improved understanding of real-world commercial demand
Stronger investment confidence
Behavioural intelligence supported more evidence-led decisions
Improved district visibility
Teams benchmarked engagement across multiple locations
Better recovery tracking
Live movement signals replaced delayed reporting cycles
Related Case Studies
Challenger Coffee Brand Site Selection Case Study
A UK challenger coffee brand used huq's footfall data to identify high-potential sites, avoid oversaturated markets and outperform larger rivals.
How JD Sports Used Customer Catchments to Inform Outlet Expansion Strategies
huq's mobility location data enabled JD Sports to refine customer catchment analysis, optimise store network performance and make data-driven expansion decisions, reducing risk and enhancing strategic growth.
.svg)
Empowering strategic teams with the world's most accurate and accessible location intelligence.
Contact
.svg)