Use Case

Building a Behavioral Variable in Response to COVID Patterns

Accounting for neighborhood differences in return-to-work patterns using mobility data

Use Case: Building a Behavioral Variable in Response to COVID Patterns

The Problem

As America returns to the workplace, traffic patterns that signal the level of recovery can be drastically different between downtown, urban, and suburban locations. Average regional patterns do not reflect a Restaurant brand’s particular location profile. Restaurant marketers want to know how COVID behavior patterns are impacting foot traffic at THEIR store locations!

The Solution

At in4mation insights, we use brand-specific customer mobility data to identify spatial service areas for restaurant locations. Service areas + mobility data enable a customized and behavior-driven Return-to-Work variable that is optimized to predict baseline performance for any brand, even amid uncertainty in COVID recovery.

Results & Key Learnings

Improved baseline predictions lead to better estimates of incrementality that drives decision-making. Major prediction improvements result for in-store and digital sales channels by accurately capturing channel-shifting behavior associated with COVID.

1
Macroeconomic indicators that were once predictive in marketing mix became skewed due to COVID. Typical seasonal patterns were disrupted.
2
Our measure of Return-to-Work is developed from observed behavior over time and space. It identifies and accounts for shifts in consumer behavior, even when patterns differ by geography.
3
Suburban foot traffic has returned to pre-pandemic levels, but urban (-11%) and downtown (-78%) trends are still down significantly from January 2019.


For more information, contact us