in

How Bengaluru-based Entropic Tech decodes user emotions to help brands win customers


Can artificial intelligence accurately gauge what you might feel when you look at a new product? It might sound far-fetched, but that’s exactly what Bengaluru-based Entropik Tech is helping its clients achieve. In CEO and co-founder Ranjan Kumar’s words, they “help brands understand their customer experience from the lens of their emotional behaviour”.

This decoding of user emotions is expected to be more accurate that traditional surveys. Kumar cites the example of an e-commerce platform that wants to launch a new mobile app. The company can set up a test where select users go through the new app, and Entropik’s Tech will track their facial expressions and eye movements as they scroll through and record engagement levels as well as reactions like happy, sad or excited.

Kumar says this results in analytics for everything from a mobile experience to an advertisement or just a piece of content. Their key areas of focus are digital experience, content experience, and retail experience, he adds.

Entropik’s clients include Procter & Gamble, Flipkart, Tata Consumer Care, Accenture and ViaCom18 to name a few. A new use case is where ed-tech companies are trying to track engagement in online classes.

But how does the emotion AI work?

The five-year-old startup has spent its first three years building this technology from scratch. It has also filed 17 patents on the subject and claims to have the second largest repository of emotion data globally after MIT’s Media Labs. The company’s models have trained on 30 million emotion data set, and are adding millions more each month.

What Entropic has done is used the latest camera technology to track and capture facial expressions and eye-blink rates in real-time. These reactions are then studied by the deep learning model, which deciphers what a certain expression means.
“We are able to track where exactly you’re looking on the screen as well as. Are you attentive enough, are you engaged enough to the whole experience, etc,” Kumar explains.

Ranjan Kumar, CEO and co-founder of Entropik Tech. (Image via Entropik Tech)

Entropik also relied on brain mapping to create their models, where an EG headset is used to track the neuro pulse of the users as they are watching an ad or going through any of the stimulus experiences. These brain wave frequencies also gave the company a good understanding on how to look at the behavioral data, especially for accuracy.

“We also look at what kind of face expressions people have when they’re watching a certain kind of content and then simultaneously we’re tracking that from brainwave mapping. We cross trained our facial coding models on that, and that’s how we set up our first one,” he adds. The company also has a repository of what they call as ground truth data, based on defined models in behavioural psychology, where a certain face expression is associated with a certain emotion.

And what is the benefit for clients?

According to Entropik’s CEO, the range of emotions captured can give a more in-depth analysis to their clients. For user experience (UX) and user interface (UI) managers, this analysis can help improve the website or mobile experience in a more optimised way. “Let’s say Flipkart is looking to have an app live. They do this testing. We track second-by-second as a user is going to make a purchase, where users are happy, where they’re excited, what are they looking at or noticing, etc,” Kumar elaborates.

The company also has its own participants and respondents based across countries who have signed up for the platform and participate in such tests. All users give prior consent before they join these tests.

Along with helping make the investment on ads more optimal, this AI-tech is also being used get reactions to packaging. “In a virtual environment, users can go through a whole shelf, which includes the clients package and a bunch of competitor packages. We track from the eye-tracking where exactly do they look, how much time they spent on a particular package of the brand versus the competitors,” he says.

This technology is not easy to replicate and Kumar has around five competitors worldwide. While the tech might be new, it is solving an age old problem for brands: how to gauge consumer reaction and accurately.

“Historically all these brands have been relying on surveys and focus group discussion. We are sort of placing our bets on that 95 per cent of consumer behaviour is pretty subconscious, only 5 per cent is what is conscious. And that’s where we have a lot more deep dive qualitative analysis. We are able to provide that value and the customers are able to see consistent returns on investment (ROI),” he explained.

For Entropik Tech, the next plan is to expand to markets such as the United States and Europe where they see a huge opportunity for the kind of technology and consumer insights they offer. The company has raised $8 million in funding from US-based hedge fund Falcon Edge in September 2020 which they will use to scale up their operations further.



Source link

Sea otters maintain remnants of healthy kelp forest amid sea urchin barrens — ScienceDaily

Apple partners with Common Sense Media to curate podcasts for kids