We are loving Entrupy, our AI designer goods authentication partner

by HULA , October 4, 2018

As a retailer which sells pre-loved designer goods, the most crucial thing to us is ensuring that our products are authentic. That’s why we have started to use Entrupy, an AI authentication service which could give triple guarantee to you and ourselves that what we sell is the real deal. By using the Entrupy camera gadget and app, we would be able to capture microbic details of handbags and accessories, upload them to the app’s server to be analysed, and provide you a certificate of authentication for a product.


Watch this video to see how your bags get authenticated.. it’s pretty cool!



To find out more about Entrupy, we also caught up with Deanna Thompson, Customer Success & Evangelist at Entrupy to learn more!


What inspired the founding of Entrupy?

Launched in 2012, we built Entrupy as a scalable and versatile platform in response to the rapidly growing counterfeiting issue and the need for trust when it comes to purchasing luxury goods. Globally, counterfeit products are a $900 billion industry, contributing to not only to brand dilution, but to organized crime, child labor and other human safety risks. With Entrupy, we’re combating this problem with a technological solution that is more accurate and consistent than the current, manual methods for detecting counterfeits.

How does Entrupy differ from other luxury goods authentication services?

Entrupy is the world’s only AI luxury handbag authentication solution. We utilize high quality data collected to teach our algorithms to differentiate between fake and authentic items, which in turn, gives us the ability to produce results with a 99.1% accuracy rate. Every item that’s authenticated helps improve our algorithms, creating a smarter solution that adapts to the changing world.

What is the biggest challenge about creating Entrupy?

It can be really challenging to source counterfeit products at scale to help our algorithms, but the biggest challenge we faced when creating Entrupy was learning the intricacies and differences between authentic goods versus fakes.

What is the quality about Entrupy’s special camera gadget that allow it to help with the authentication process?

When authenticating, our handheld device along with our IOS app are used to take microscopic images of different regions and then upload them to our server, where our algorithms determine whether the item is authentic or ‘unidentified’. If the item is authentic, an authentication certificate is instantly produced within the app which they can then print, text, email or share on their product listings.

With the vast variety of designs and details involved in even just a single brand’s products over the years (for example a Chanel bag produced today has different details from one products 30 years ago), how do you keep up with or gather data about all the range of authentic designs?

Entrupy’s technology is a mix of machine learning and microscopy. We train our machine learning algorithms to pick up data points from millions of microscopic images looking for qualities like texture, contrast, topology, geometric shapes, thread-counts, minor manufacturing artifacts such as scratches in the hardware stamps, wear, and many more details that you wouldn’t be able to easily see. These details are in fed into our custom machine learning pipeline, allowing us to determine a product’s authenticity.

Why are Hermes bags historically more difficult to authenticate?

Hermes are a brand unlike many others, largely due to their idiosyncratic approach to scaling manufacturing and positioning their brand. Since we focus a lot on manufacturing and workmanship, we notice that their work is much less standardized compared to other brands — artisans have their own stamps, the workmanship is unique to each factory, era or artisan. This makes it much harder for counterfeiters and authenticators in general, because if there is no standard to follow, then how do you determine what’s the right on?. However, our systems are designed to allow for that variation, which is why we have been pretty spot on in our services in authenticating Hermes products.

Do you think this process will eradicate fake goods or will there always be black market goods?

As much as we are growing in size and spreading trustworthiness, our work is a drop in the ocean. The menace of counterfeit products will always exist in some form or other, even more so in the future, because of how much easier it is to ship products on a global level. And as long as there is the demand for them, they will exist. As a matter of fact, even if there isn’t demand for them, there is a burgeoning counterfeit industry for regular home goods which has arisen because of global marketplaces that haven’t policed their own house very well.

What do you think are the biggest ways technology would disrupt fashion in the future?

I think through AI. AI has changed that perception by proving to be valuable in the fashion world. Thanks to AI, consumers now have more personalised choices and a much friendlier user experience, especially with in-store kiosks and recommendation engines. It has also helped streamline laborious aspects of production for manufacturers and distributors. However, since AI works better with more accurate data, we are yet to see its true power as there is still some way to go in understanding and mapping consumer behaviour over time and adapting to it. Essentially, there’s is a world of potential for AI in the fashion world and we’re at the beginning of the arc.

What is next for Entrupy?

We are actively working on collaborating with multiple brands, as well as expanding our product categories across other high-end products. We are also very excited about the release of our latest product, Entrupy Fingerprinting, which will add another layer of protection higher up the value chain – for manufacturers and retailers. Our global business is expanding every week and we have a growing market in Asia. These are our future priorities!