Home / Blog / Watch out, they are watching you …

Watch out, they are watching you …

Security cameras are quickly becoming part of every ambient. And they do more that looking after security… Image credit: Iride Analytics

Security cameras have become ubiquitous and are now starting to being used as image sensors to harvest data about the behaviour of people. This goes quite beyond their original goal, and yet it makes perfect sense.

I remember few years ago the Data Analytics Lab of TIM (at that time it was Telecom Italia) teamed up with the MART, the Museum of Modern Arts in Rovereto, to run an experiment in the museum. The goal was to track people movement in the various halls and analyse how long they would stay in front of a piece of art, then to see where they would go next, if they would come back to see it again. No information on the identity of a visitor was kept, the behaviour was associated to a few classes of visitors, automatically detected (young, grown up, middle age, elderly, male, female…).

The museum curator had the opportunity of experimenting by changing the disposition of the various items and then evaluate the different level of attraction on visitors.

Now I see that there are services tailored to shops doing basically the same thing: detecting shoppers interest in what is showcased in the various shelves.

Take IRIDE Analytics, thanks to Andrea Giacchino, who is working in the area of improving marketing capabilities in retails, for pointing it out to me. They are providing a service of data analytics to pharmacies (hence a very focussed service) based on data harvested by security camera.

They can count the number of people stepping in in the store, create a heatmap of the points that are attracting (more or less) visitors’ attention and how long they stay on average in a specific location, create a map of their whereabout in the store as they are waiting to be served. The service is also monitoring the waiting time providing help in rightsizing the personnel in the pharmacy.

Additionally it creates a profiling of clients by age and gender, and calculates the revenues by square metre (based on products displayed and picked up by the clients). Actually the system cross check the data of products picked up by a client with the ones actually sold at the counter… This ensures accuracy and can also detects any attempt of stealing the merchandise…

It looks to me that IRIDE by focussing on a specific type of shop, pharmacies, can deliver good value tailoring the analytics to the need of that specific market segment. Clearly, it wouldn’t be a big step to rethink the analytics for a different market segment and I guess that in a very short time most shops will take advantage of image recognition technology and data analytics. Notice that all the basic ingredients are there: you have digital POS, every item has a bar code and a unique identity, security cameras are becoming a standard fixture in any public space. Many shops, in addition, have some sort of fidelity card that allows the profiling of clients. Put all this together and season it with data analytics … welcome to the new retail space.

The downside, of course, is that our privacy fades away. But don’t worry. Every shop will be keen to state that they conform to the GDPR (in Europe) and they are not -actually- watching us. Up to you to believe in their claim. Most probably you, as I, would not mind.

 

About Roberto Saracco

Roberto Saracco fell in love with technology and its implications long time ago. His background is in math and computer science. Until April 2017 he led the EIT Digital Italian Node and then was head of the Industrial Doctoral School of EIT Digital up to September 2018. Previously, up to December 2011 he was the Director of the Telecom Italia Future Centre in Venice, looking at the interplay of technology evolution, economics and society. At the turn of the century he led a World Bank-Infodev project to stimulate entrepreneurship in Latin America. He is a senior member of IEEE where he leads the New Initiative Committee and co-chairs the Digital Reality Initiative. He is a member of the IEEE in 2050 Ad Hoc Committee. He teaches a Master course on Technology Forecasting and Market impact at the University of Trento. He has published over 100 papers in journals and magazines and 14 books.