DataSentics

AML and Fraud detection

Introduction

Fraud/AML investigation is costly due to its high human resources demands and a constant need to adapt to new methods used by fraudsters and money launderers. However, with the help of machine learning, these costs can be reduced significantly.

Business case

Current fraud/AML systems may be ineffective due to high false positive rates and are not adapted to conditions of increased efficiency. As a result, fraudsters and money launderers adjust to the existing detection rules and develop new unrecognized methods. Typically, this requires a combination of the following approaches:

  • Extreme prejudice in fraud/AML rules (and therefore revenue loss from client rejections)
  • High staffing demands for fraud/AML specialists checking each flagged case individually and leads to additional wage costs
  • Increased AML and fraud risk if the other two approaches are relaxed

Solution

We provide a custom open platform to decrease false positives/alerts and increase the number of true positives or actual frauds. Reducing staffing demands of fraud/AML investigation and speeding up the process by:

  • Providing investigators with an interpretation of the reasons/triggers for suspicion
  • Prioritizing the level of distrust and thus enabling investigators to focus on a smaller number of high-risk cases

Reducing risk of fraud and money laundering by finding new cases and patterns with the help of machine learning methods.

Benefits

  • A custom platform where you own the underlying code
  • Identify new fraud/money laundering patterns
  • Reduce workload by better prioritization of suspicious cases