We live in a world filled with data - online data, shopper data, purchase behavior data, big data, and much more … data. Most of this data is created by our actions within technology as opposed to our actions and reactions in the physical world.

In the physical world it’s hard to contextualize basic demographic data, even simple statistics like gender and age, not to mention interest levels, emotional analysis, or even for that matter, true recognition of identity. The fact is that we do now have some real-world analytical tools available to measure some offline activity. This is something that fascinates us and which, on the whole, we are obsessed with.

Most people, when first exposed to this kind of data, give us an “Ok, cool!” (nerdy high-fives all around) type reaction but then they don’t really understand what to do with this data, because dealing with real-world/real-time analytics is frequently uncharted territory for many developers and marketers.

To be successful with real-world analytics tools we have found it’s best to focus on one, or some combination of these opportunities, that best suit your situation.

1. Establishing ROI / Value

Are you displaying products, signs, promotional end caps, or anything else that you might want a potential customer to focus on? If you are, then there are real-world analytics tools that can be used to provide you with data. By having a camera included in your display you can obtain data on such things as the number of people that pass your display, the number of people who stop and look at your display, and how long they spend looking at it.

This allows you to measure physical engagement in ways that are very much in line with digital thinking. For instance, how many thousand people pass by the camera per day, and how many people look at the display for more than five seconds? Sound familiar?

This has all of the advantages of the standard online model, recognizing CPM (cost per thousand) in conjunction with CPE (cost per engagement).

So, in an offline marketing environment you now have the capability of creating the same data as in the online environment, with comparable measurements to your online media investments, which can help with decisions to drive future spending.

With the availability of this offline data, you now have the opportunity to establish key performance indicators (KPIs), which mean that ultimately a measurable return on investment (ROI) for offline marketing is now possible.

2. Research

How many of your friends would actually publicly admit to watching Twilight or liking Miley Cyrus? What percentage of your friends, on the other hand, do you think might like these things in private, but not admit it?

Emotion analysis, driven through facial cues, is a powerful tool for identifying subconscious emotional reactions to stimuli ranging from ads to how a user might interact with a physical or digital experience. If a user smiles with contentment when they look at that huge movie poster depicting Miley Cyrus, you know that you are picking up something that they may not frequently admit to. Of course, in that situation, it is highly unlikely that they would buy the Miley Cyrus poster to go on their bedroom wall, but you might be able to encourage them to take their younger relatives to see the movie, as a “family duty”.

Attention span can also be used as a measure of intent or intrigue. The longer somebody looks at some form of promotion, the more they are clearly interested in it. It is possible to alter content on a display, dependent on how long somebody stares at it.

This PepsiMax YouTube video, depicting an “unusual bus stop” in London, shows an example of how content can be adjusted to match the interests of people nearby, when there is a camera to pick up on that interest:

That example was designed mainly as a prank, but imagine the amount of information that the marketers could have gleaned from the waiting bus passengers, if they had tried to analyse peoples’ reactions, particularly if they had used the full emotion detection, like there is in the Emotion Analysis Platform.

One of the organisations that was at the forefront of this sort of real-world research was IMRSV, which has been acquired by Kairos. Tim McAtee, VP Research IPG Media Lab, believes that by using IMRSV they have been able to run large-scale tests in the real world, which have brought then the data necessary for them to determine immediately whether something is working or not, compared to it taking months previously. “The real-time data this gives us about positive or negative reactions to advertising in the real world is a game-changer” he has said.

3. Triggering Real-Time Engagement

Data is a powerful tool to assist with decision making for high level strategies around your business. However it is arguably even more powerful when it is used in real-time to create personalized experiences that are customized to the viewer.

Let’s use a digital sign as an example. What would happen if you knew that the viewer was a man or a woman? Or what about two women in their 20s? What about a woman in her 40s and what appears to be one or two children with her? Each of these insights around gender and age would allow you to make some assumptions to personalize the ad.

Similarly, imagine the user-experience customization that could be done with a kiosk experience. Why not automatically start the digital experience as someone approaches and focuses on the screen for more than 7 seconds? When people aren’t focused on the screen why not shift the display into a mode designed to draw attention to the kiosk as opposed to an “engaged” mode? In fact, the bus stop example given above, could easily be adapted to follow the same model.

There is a whole area of development known as affective computing which focuses on the vital role that emotion plays in communications between people. The leader in this field, Rosalind Picard, believes that if “we want computers to be genuinely intelligent and to interact naturally with us, we must give computers the ability to recognize, understand, even to have and express emotions”. She believes that “emotion has a critical role in cognition and in human-computer interaction”. Affective design takes this further by attempting to define the emotional relationships between consumers and products. Technology has now got to the point where it is possible for computers to detect emotions, and react appropriately, on an affordable scale.

One example already in use is Unilever’s smile-activated vending machine. This takes one part of emotion analysis, smile detection, and utilises it to reward people who produce a large enough smile aimed at Unilever’s display. The result was that not only did people take notice of the Unilever display, they caused enough of a commotion to encourage others to come and participate in the fun.

Another original use for smile detection occurred at a Pay Per Laugh series of comedy shows by an independent theatre company in Spain called Teatreneu. Facial detection cameras were placed at each seat in the theatre. Throughout the performance patrons’ smiles were constantly detected, and the amount they had to pay depended on how often they smiled.

In the future, imagine the possibilities that there could be if you also incorporated facial recognition into your advertising displays. Of course, you would have to think very carefully how this was implemented , otherwise you could be in danger of outing the closet Miley Cyrus fan mentioned above, if public displays started pitching Miley Cyrus material to him.

Conclusion

Methods of marketing and the ways we can analyse results have changed markedly over the last few years. But crucially, we are now at the point where we can use digital solutions to help us perform in non-digital settings.

Thanks to video facial detection software, allied with emotion analysis, it is easier than ever to establish how potential customers really feel about the content of the marketing displays they encounter. All it takes is a camera in each display, allied with the appropriate software, to be able to get into consumers’ minds. Do they like what they see? Are they bored? Is this the right product or service for them? How well is this advertising display working? Are the analytics proving the display's success or otherwise?

Just as easily you can use the same software as a research tool. What interests people as they pass this spot? Who takes the most interest? Are they mainly older people, younger people, males or females? All this can be determined by simply putting some form of display in a particular place, with a camera making observations.

Kairos now has solutions for marketers who want to make the most of their environment, and for developers who want to create software that collects and analyses this kind of real-world information. Contact us for details of how we can help you.