E EREACE
Back
Reduce losses and riskMarketplace / E-commerce - Customer Service and Loyalty

Detect Fake Review Farms in a Marketplace

A marketplace with 40,000 sellers suspects that some are buying 5-star reviews, now written with generative AI and hard to distinguish by the text. The tactics change every month and there are hardly any confirmed cases. Buyers are starting to distrust ratings and consumer authorities are watching this fraud.

Estimated annual impact on EBITDA
+€2.55M
Marketplace with €1,200M of sales. Illustrative example with indicative figures: replace them with your own company figures.

Where the money comes from

Sales protected by greater trust in reviews
+€2.50M
Penalties and claims avoided
+€400k
Cost of the investigation team and model
-€350k
Annual EBITDA impact
+€2.55M
Adds profitReduces profitSystem cost

What to do now

  1. 1Score accounts and sellers by how unusual their behaviour is.
  2. 2Investigation team on the weekly top 50.
  3. 3Keep confirmed cases for a supervised model.

For your committee

One page with the decision, the impact, the risks, the steps and the KPI to track.

The print dialog opens: choose "Save as PDF".

Watch out: more volume is not always more profit

Fake reviews inflate sales in the short term and the marketplace earns commission on them; tolerating them looks profitable until the trust of all buyers falls.

KPI for the committee

% of investigations with confirmed fraud and trust in reviews.

Detail for your data team

Proposed technique: Isolation Forest

Why: There are hardly any confirmed cases and the tactics change; moreover, AI-generated text is indistinguishable. Behaviour, however, gives it away: new accounts that review 30 products from the same seller in one hour. Isolation Forest isolates those rare patterns without needing labels.

Cost of getting it wrong: Letting review farms through erodes trust in the whole marketplace; accusing an honest seller creates conflict and possible claims.

Data needed: Reviews: date, rating, length, product, seller.; Behaviour of each account: age, purchases, reviews per day, devices, IP addresses.; Seller patterns: review spikes after launch, reviews/sales ratio.

The Ereace system

Test decisions with synthetic people before you test them with real ones.

This tool helps you decide with numbers. Before you invest, understand, test and rehearse the decision with the people involved: your customers, your team or your committee.

Understand
QualiSynth

Before you invest, find out what your customers think, need or reject about the initiative.

Test
StrataSynth

Put the offer, the message or the journey in front of synthetic people who do not always follow the happy path.

Train
ArenaSynth

Rehearse the committee presentation or the vendor negotiation against synthetic decision-makers.

See all Ereace products

About this tool. It is free and made by Ereace, an AI-native product studio and human intelligence ecosystem: it connects real human signals, synthetic people and the systems built around them, so teams can understand, test and act on human behavior before decisions reach the real world. About Ereace

Comments or suggestions? info@ereace.es