bleckwen logo

Bleckwen

Bleckwen’s AI model increases detection rates and generates half as many false positives.

We take the data of our partners and make it useful. Our team creates smart models by combining their data, enriched with ours, to solve their particular needs.

By constantly analyzing the models for drift and effectiveness, we retrain them as needed, saving businesses time, effort and money.

HQ: Paris, France

Founded: 2018

Fraud Solution Profile

Bleckwen

Our adaptable solutions for credit actors bring data science to the frontline of your lending businesses.

  • Powerful and easy to integrate API solution with well-documented REST APIs
  • Get results fast without disrupting your business operations

 

A flexible API for easier and faster integration​ to minimize fraud losses and reduce operational cost​ ​

 

 

Use cases

Personal loans

Personal loan fraud is a growing challenge for large companies. Our model reduces  fraud by 80% using an efficient scoring tool to minimize the impact of false positives. The longer it runs on historical and real-time data, the more accurate the rules become to reduce fraud over time.

 

Auto Loans

While most application fraud targets identity fraud, our solution uses data from our auto lender partners to predict and find all types of fraud in a single integrated fraud score. The alerts enable business owners to prioritize the highest-risk transactions for approval by avoiding: identity and income forgery, straw lenders, merchants, and collateral fraud.

 

Retail Credit Applications

Our data scientists use machine learning techniques combined with unique retail data to minimize application risk, and ensure an optimal customer experience at the point of sale. Our analytics model is highly predictive and helps retailers identify high-risk applicants who are more likely to fail due to application fraud.

 

SME Loans

SME fraud loans are increasing dramatically. The challenge is how to limit fraud exposure and contain the impact of customer attrition. Our model is based on data enrichment and accurate fraud scoring meaning every decision is based on facts, not assumptions.

 

 

Customers

BNP Paribas
Carrefour Banque & Assurance
DIAC, Mobilize Group
PSA Finance
Credipar

 

Industry
Financial Services
Primary Functionality
Fraud Platform
Fraud Type
Payment Fraud, Synthetic Identity Fraud
Technology
Behavioral Biometrics, Machine Learning, Rules Engine