Automated system can detect counterfeits sold online

A team of researchers from the US have developed an “automated assistant” system that can calculate the likelihood a product is counterfeit based on its online customer reviews.

The researchers from Georgia Southern University and Virginia Commonwealth University showed their model could process customer reviews to calculate a counterfeit score, which was then found to affect trust and perceived risk and consumer attitude towards the purchase.

The research is published in the journal Decision Support Systems.

“Product authenticity in the online marketplace is a common issue plaguing consumers. The decision process involved in determining product authenticity is lengthy and complex. Despite the pressing need for an automatic authenticity rating system for online shopping, little research has been done to develop such a system and assess its effects on consumer purchase behaviour,” the researchers said.

“To respond to this need, our study develops a design artifact, called OnCDS, to automatically calculate the likelihood that a product is counterfeit based on online customer reviews.”

The researchers note the challenges facing consumers in trying to authenticate products when shopping online, such as the need to review a large volume of qualitative information, which can be both positive and negative.

Instead, the researchers believe an information systems approach using big data analytics – and bringing together design science and behavioural science paradigms – can remove these challenges and support the consumer’s decision making.

The study involved the researchers designed an automatic counterfeit scoring system, called Online Counterfeit Detection Score (OnCDS), and tested its utility based on consumer behaviour.

The system used a number of analytical techniques to process customer reviews, such as analysing the tone and language of the review, to determine a counterfeit score on the likelihood the product is a fake.

“As the consumer browses the online marketplace, a browser add-on facilitates communicating with the online marketplace, and OnCDS ultimately returns a counterfeit score to the consumer,” the researchers said.

The researchers were able to validate the system where research participants were found to agree with the OnCDS generated.

The researchers then found that displaying a counterfeit score in an online marketplace affects a consumer’s perceived risk and trust in the product, which influences their decision making and purchase behaviour.

“Implications for practice include supporting a consumer's decision process via alleviating the issue of determining a product's authenticity. Online marketplaces have long employed trust seals and other mechanisms to improve consumer confidence in the marketplace. This research has illustrated yet another dimension to influencing consumer trust in products via implementing an automated counterfeit score,” the researchers said.

They added: “Practitioners can expand upon or further refine the counterfeit score calculation to improve accuracy or adaptation into their online marketplace or website. Furthermore, understanding how perceived risk and trust can influence a consumer’s attitude toward a purchase can aid in improving sales and overall perceptions of an online marketplace or website.”

The system was developed on the Chrome Browser and Amazon marketplace, but this could be extended to other browsers and marketplaces, the researchers said.

The team are now looking to expand the research to more rigorously assess the model.