Using cameras and people counting technology, American supermarket giant Kroger has reduced queuing time for its customers from 4 minutes to just 26 seconds – according to the Kellogg School of Management’s Operations Room.
Cameras sit at the entrances and above cash registers at most of Kroger’s 2,400 stores. The system detects people entering the shop and predicts for each one how long those customers spend shopping based on time and day. It then determines the number of lanes that need to be open in 30-minute increments so supervisors can deploy cashiers accordingly.
Stores have long been able to use traffic counters to build a forecasting model of customer arrivals. Video store traffic counters, for example, are 98% accurate and can differentiate between two adults walking in and a child trailing a parent. Drawing charts over time reveals obvious patterns of how many people tend to enter the store each day and at what time. Store managers will know, for instance, that every week at 6 pm on a Friday store traffic doubles.
Combining this data with queue monitoring – where the system logs the number of people in queues and at checkout tills – gives a model of how long shopping trips are and how they might vary by day of the week and time of day.
This is good for long term planning, but what about when an unexpected influx of customers enter the store? As systems report in real-time (ours updates every minute) and supervisors know how long people spend shopping, shortly before queues are predicted to form they can take staff off other duties like stocking shelves and deploy them on the tills.
Managing Queues, the Retail Sensing system