Firms in the Asia-Pacific region are set to greatly increase their spending on big dataRead More
Filling the shopping gap for retailers
Retailers love to know when they sell things, but they would love to know even more when they don’t.
What would your average merchandising, buying, promotions or retail operations VP give to know all the occasions that someone picked up their cherished merchandise and put it down without buying? It’s agonizing. I recently talked with some very interesting people from a large trucking station in the US, who told me they had taken to scrolling through the security camera archives to better understand their customers’ shopping behavior.
Clearly there is a demand for a clear picture of what’s happening in-store, after the footfall counter, but before the checkout. I was mightily impressed, therefore, to hear of two emerging firms – one from the UK and another from Silicon Valley, who can analyze data from security cameras to “fill the gap” between footfall counters in retail outlets and the stores’ point of sale (POS) systems. Online, the technology is more established. Counting abandoned baskets is quite well-advanced, but it’s always been a challenge to understand the browsing and basket filling behavior of the customer in-store.
Equally hard to deal with is the evermore resilient and inventive behavior of shoplifters and their thieving methods and patterns. I was just wondering when we would find a solution to this problem when, lo and behold, Renasense turned up on our website looking for a way to mash up more data with details from the security cameras.
You may be more advanced in your research than I, but I was impressed to find that Renasense provides a system that allows business users to capture data, count events and people, calculate and alert other systems all based on extracts from moving AV images on the existing security camera network.
It’s this combination of needs that brought Renasense to Kognitio, with its engineers looking for an engine that could handle the ability to capture the events and movements on the cameras and combine them with all the other business data about customers, products, store layouts and staff. The Kognitio in-memory analytical platform is ideal for complex integration and high volume, complex analytics. Talking to our friends at the truck stop, we found they were excited about the ability to integrate analysis of sales at point of sale with their customers’ physical movement through the parking lot and restaurants, as well as in the retail section of the truck stop. Their imagination was very much fired up when we discussed the capability of understanding who moved in front of what retail promotions and products, versus the number of sales or what the stock management system was ordering.
They immediately saw a big influence on promotional layout, which was in addition to the benefits of watching customer movements where restocking cycles outpaced sales cycles. Thinking about this brought the realization that not only could they see which items thieves were staking out and from where, but also where they were taking them in the store, and secretly breaking the security packaging so they could skip past the security scanners undetected.
It seems just looking at movement throughout a store is not enough to detect theft, as well as to plan better layouts and security. They realized that they needed more information; adding data from sales, stock and staff scheduling systems could help them predict and deploy their resources more effectively.
All of this is new to me, but it’s a great example of how more companies are seeking Big Data solutions that move beyond the theoretical and into the day-to-day practical. I think at last I see a solution that gives the bricks and mortar retailer the same granular understanding of the online basket tracker. I’ll keep you posted on what’s happening, but I can’t see in-store promotions being the same after this.
And if you’re a shoplifter, things just got a lot more difficult for you. To which most of us would say, “Good!”