Problem solve Get help with specific problems with your technologies, process and projects.

Machine learning is transforming brand protection

Marc Andreessen, founder of Netscape and now a pre-eminent Valley venture capitalist, says “software is eating the world.” Algorithms available on-demand in the cloud and on our smartphones are changing the rules for every facet of our lives. Now machine learning is changing how consumer product brands fight back against the $1.2-plus trillion in revenues lost to counterfeit and supply chain integrity issues each year.

Counterfeit products and gray market imports prey on the quality, good will and trust brands have spent years and billions of dollars building, sucking profits and impacting consumer trust. The problem is not a new one. A running battle has been fought for decades between brands and fraudsters. A sort of arms race is ongoing, with brands investing in special labelling and packaging designs, invisible inks, complex packaging materials — all in attempt to outwit the fraudsters.

With headline growth challenged and the integrity problem escalating, brands can no longer simply accept the status quo and absorb integrity losses as a cost of doing business. The numbers tell the story — traditional solutions simply aren’t working effectively. The good news is software intelligence and the mass-scale digitization of the world’s consumer products is coming to the rescue.

Switch-on the data intelligence

In large part, the issues of counterfeit products and gray market imports stem from a lack of visibility into the supply chain. If brands knew where every single product item is as it moves through the supply chain — where it was made, how it got there, when it reached the retailer and, ultimately, when it was purchased by the customer — brands would know if the final product is genuine and/or in the right market. Achieving this kind of visibility hasn’t been possible until now.

The introduction of mass-scale product digitization is revolutionizing the consumer product market:

  • Every product can now have a web address with the global upgrade to barcodes underway with advent of GS1 Digital Link;
  • Brands have the capability to gather data through billions of smartphones already equipped to scan barcodes;
  • Mass-scale, crowd-sourced data from consumers allows brands to continually redefine and grow revenue based upon real-time intelligence; and
  • Cost-effective, real-time data collection throughout the product’s supply-chain journey.

Digital identity technology in the cloud can make all of this possible. Digital identity systems generate real-time data and capture everything that happens to, or about, each individual product throughout its lifecycle, from manufacturing to recycling. By creating a dynamic digital ecosystem around the world’s physical products, brands have an opportunity to change the integrity management game.

A new era of authentication with machine learning and IoT traceability

The challenge until now has been the cost of detection. Previously, the only way brands could track products and protect brand integrity through the supply chain required cost-prohibitive hardware and a lot of people — teams of brand protection experts — to identify problems in the market.

Until now, the hardware used to detect and deter counterfeit and gray markets has taken the form of proprietary codes, invisible marks, tags or specialized packaging. Proprietary apps or devices have been required to check tags or codes in the field. No surprise, the limitations of these technologies are numerous and ultimately terminal.

Adding hardware-based tags and labels to products is expensive, driving up bill of material and production costs, slowing production throughput and complicating production scalability. And the cost is building as counterfeiters innovate and new tag types are required.

The reality is the vast majority of product volume never gets inspected and hence the majority of issues are never detected. And in terms of direct consumer engagement, proprietary apps are typically required, which means consumer participation is low.

Good news. Software algorithms with predictive intelligence have arrived, helping brands not only protect against but also stay a step ahead of counterfeiters at scale. Data gathered from products as they’re manufactured, distributed, retailed and consumed is aggregated in the cloud while machine learning algorithms trained to look for patterns are able to apply this data to identify suspect events. With this intelligence, brands are taking a proactive stance against brand integrity issues.

Enter GS1 Digital Link

The barcode upgrade with GS1 Digital Link means costly proprietary tags on products costing 10s of cents per unit can now be replaced with web-connected QR codes costing fractions of a cent per item.

  • Real-time data is gathered by scanning products with smartphones without any proprietary applications, both in the supply chain and in the hands of the consumer.
  • Data is organized in the cloud with each product item’s digital identity.
  • Machine learning algorithms apply real-time analytical intelligence to the data.

It’s a model that cuts costs, dramatically increases the volume of data captured, delivers visibility in real time and applies the full strength of computing intelligence to each and every product items journey.

Machine learning quite literally means that a machine programs itself by learning from data, finds answers in the data it collects, learns patterns of what is normal and what is not, and learns to identify when things happen outside of these norms.

Cheap and abundant processing power, big data and improved algorithms have all contributed to the practical application of machine learning. And now it’s able to be applied with product data at massive scale to change the way companies and/or manufacturers operate supply chains. Unlike traditional software programming, which is limited to the rules and vision of the software coders, machine learning offers tremendous advantages by reducing the programming time for problems with a complex network of rules, and the ability to attack seemingly “unprogrammable” tasks — beyond the human brain’s capacity.

Fighting fraudsters with software and machine learning in the cloud

If a brand inspector were to be present at the manufacture of each product item and then accompany it throughout its lifecycle from distribution to recycle, problems of illegitimate production, diversion in the channel and counterfeit at the point of retail would be eliminated. But clearly that would be at absurd cost, not to mention the carbon footprint of the airlines involved.

This said, product digitization coupled with machine learning delivers on the same level of fidelity, with the digital identity in the cloud acting as a virtualized brand inspector accompanying each product on its journey — its machine-intelligence brain scrutinizing each step along the way. Consumer product brands can now follow individual products, each with a unique digital identity, throughout the product lifecycle. This provides unprecedented data analytics and real-time traceability.

If a product is headed toward the wrong channel of distribution, it is detected. If a product identity appears in the wrong market or the wrong pattern of events surrounding a product creates suspicion, it is detected. Every consumer engagement becomes a data point to support integrity enforcement in the supply chain. And when an issue is identified, because every product item is uniquely digitally identified, the source of the problem is rapidly identified.

According to the Organisation for Economic Co-operation and Development, 2.5% of global imports are counterfeit, with U.S., Italian, French and Swiss brands most affected. For companies losing tens of millions of dollars every year, now brand protection is available to any brand, consumer or retailer using a regular smartphone and industry-standard product codes. Mass scale, low costs, pre-emptive intelligence for every product item. Software is changing everything.

All IoT Agenda network contributors are responsible for the content and accuracy of their posts. Opinions are of the writers and do not necessarily convey the thoughts of IoT Agenda.

Data Center
Data Management