2014 · 25 citations · 5 references
ComputingInformation TechnologyRetail ManagementInternet Of ThingsRetail AnalyticsSensor FusionCustomer Behavior AnalyticsIot AnalyticsIot Data AcquisitionIot Data ManagementIot SensorsRetail Technology IntegrationBig Data Analytics ArchitectureInternet Of Things ApplicationsIot MonitoringOut-of-stock MeasurementPrecisionRetail Analytics SystemsShelf AvailabilityShopper Decision Making
In today’s customer‑centric retail environment, on‑shelf availability is essential for shopper experience and loyalty, yet manual approaches often fall short and can hurt retailers. The study proposes an automated IoT/IoE model, incorporating multiple sensor configurations and a predictive algorithm, to ensure precise on‑shelf availability. The model employs sensors and big‑data analytics to process multi‑source information, notify store associates, and uses a multi‑stage cross‑verification algorithm to predict and prevent out‑of‑stock situations. The approach improves operational efficiency, reduces costs, and enhances shopper experience.
In today's customer centric world, enabling shopper experience is a very important factor in maintaining customer loyalty. On shelf availability (OSA) of the product that the customer is looking for is a key metric in ensuring shopper experience. Current manual approaches to enabling OSA have gaps and might fall short of customer expectations and impact bottom line of retailers. We propose an automated Internet of Things/Internet of Everything (IoT/IoE) enabled model for ensuring OSA. The use of sensors and big data analytics helps process data from various information sources to generate information about out-of-stock products on the shelf and notifies the store associates to take actions to stock up the products on the shelves. The precision level of such approaches could vary and hence we look at multiple sensor configurations that can be used in the retail segment to address the OSA needs. In addition, we also propose an algorithm for enabling OSA and an integrated architecture to precisely identify and predict trends towards out-of-stock situations. The algorithm also emphasizes on multi stage cross verification to reduce false alarms. Such a model is capable of improving operational efficiencies, reducing operational cost and improving shopper experience.
5
Andrew Senior, Lisa M. Brown, Arun Hampapur et al. · 2007 · 40 citations
Object Tracking in Video Pictures based on Image Segmentation and Pattern Matching
Takashi Morimoto, Osamu Kiriyama, Yuji Harada et al. · 2005 · 26 citations