Fake Reviews: A Five-Star Strategy to Prevent Brand Abandonment

Fraud
Attack Types
Machine Learning
Review fraud
Brittany Allen -- Sift
Oct 18, 2020
Presentations
Customer reviews can be an effective way for consumers to learn more about a product or service prior to purchasing. On the other hand, sham reviews can quickly lead to a loss of trust. Here, Sift looks at why product reviews matter and why fake reviews pose a growing problem to online retailers. The focus then turns to content moderation and a five-part solution centered on machine learning to combat phony reviews, with a set of best practices concluding the deck.

Some content is hidden, to be able to see it login here Login

Blue-tinted background of a man watching a webinar

Host a Webinar with the MRC

Help the MRC community stay current on relevant fraud, payments, and law enforcement topics.
Submit a Request

Publish Your Document with the MRC

Feature your case studies, surveys, and whitepapers in the MRC Resource Center.
Submit Your Document

Related Resources

Mar 08, 2023
Customer Recognition System - A New Tool of Detecting Fraud

Today, link analytics has been widely used across a variety of applications and industries (e.g., telecommunications, social networking, healthcare, finance ) to identify or predict the association of different entities behind the scenes. Companies with multiple product offerings use this technology to learn from their customers’ data to provide better user experiences. 

At Intuit, our customer recognition system (named Core ID, internally)  is focused on finding out if one customer or one family/close cluster uses one or more entities to register many accounts for products, such as QuickBooks Payments and QuickBooks Payroll customers. 

Normally, if the customer is identified with one set of entities, we can use existing solutions for ID-mapping, which rely on “exact” matching among entities to create clusters and graphs. However, this absolute linkage will fail if the customer is associated with multiple entities or changes entities (device IDs, IP address, etc.). 

To solve this problem, we have devised a methodology for recognizing one customer, or one household, from different angles by applying several AI-driven technologies. 

Intuit’s customer recognition system reveals relationships among different entities, serving as a complement to existing linkage-based graph analytics to more quickly identify or predict the association between customer accounts. Understanding these underlying connections more quickly is one strategy for building long-lasting customer relationships.

X
Cookies help us improve your website experience.
By using our website, you agree to our use of cookies.
Confirm