Use case: Counterfeit

Brand reputation management via anti-counterfeit

Many companies in the consumer goods sector, especially in electronics, encounter many problems with online sale of counterfeit products. This problem is growing rapidly in the last few years with the growth of e-commerce platforms and consequently online sales. But even the large legacy sites like Amazon are used for counterfeit products. In this case we describe how NLP technique can be used to trace and attack counterfeits on e-commerce platforms.

Why should you read this case study?

Is counterfeit something you fight every day? Are you side by side with your legal department talking with your resellers to hunt after counterfeits? Read this article and we will see that you can be a whole lot more effective in your work when using customer feedback analysis.

Read more ▾Contact us


of all trade worldwide is done with counterfeit products


of all counterfeit products are consumer electronics


of counterfeit products are sold on trusted e-commerce websites

How to find counterfeits through customer feedback?

Using NLP (Natural Language Processing) techniques to trace counterfeits is a complete new approach. Nevertheless Wonderflow has taken the challenge to do so for one of it’s clients that produce a large range of electronic devices for consumers (called: ‘the company’).

After extensive analysis on how to trace the specific reviews that refer to counterfeits, the system scanned serveral e-commerce platforms. The idea was to find reviews that where buyers complain about fake products. It turned out that in some cases up to 70% of the products sold on a specific website, were fake! So with the help of buyers and analysing their feedback, Wonderflow was able to find many cases of fake products.

The challenges we faced:

  • Define the right topics and words used by customers referring to fake products they bought
  • Get cooperation from the e-commerce platforms to delete traced counterfeit goods*
  • Make sure all is done within the legal boundaries

* After identifing this large group of fake listing, the e-commerce platform was not willing to take out those products from their website. Only when the company filed a lawsuit did the they begin to cooperate with the company. Untill then, not only the brand is damaged, buyers lost their money.

You may imitate, but never counterfeit


  • The company is now able to decrease counterfeit being online with 90 days
  • A conservative calculation shows that the company gained 15 million USD in not missed sales and less brand damage per year
  • Advantage for e-commerce reseller (no return, no losses, trust with real brands)


Who had thought that a data driven technique as NLP could help expel counterfeit from the internet? Within a limited time of serveral weeks, large amounts of fake products were identified and taken offline after cooperation form the e-commerce platform. Now a continuous scan is set up to prevent further counterfeit vendors to get any kind of business.

The information in this case study is confidential. Brands and company names are anonymized.

Email this case to a colleague

Get in touch

Want to know how you can become customer-centric just like our other clients? Get in touch right now and we’ll get back to you.

You are in good companies: Some of our clients