Luca has extensive strategic and operational experience that he gained at Deloitte, Deutsche Bank and Goldman Sachs. His expertise lies at the interception between process, data and technology. He has worked on creating market utilities within financial services and driven digital transformations across global organisations. Luca holds an Engineering Degree from Politecnico di Milano and he is an expert in the field of anomalous data pattern identification.

What you will hear from Luca:

Problem statement:

· The process of screening customers and transaction data against entities and in sanction lists or PEP lists is inefficient and ineffective

· Inefficiencies arise with false positives and false negatives that have to be reviewed manually

· Difficult to truly provide a risk based approach for detecting sanction risk

The key root causes for the above issues are as follows:

· Poor data quality

· Poor / unoptimised algorithms to detect name matching

· Lack of ability to “automatically learn” from reviews conducted in the past

· Out of date policies and procedures

· Mainstream customer and 3rd party screening software allow the configuration of matching thresholds, but this alone is often ineffective

· Black box algorithms require thresholds to be set carefully

Our solution

· Data cleansing and transformation

· Advanced analytics and metrics

· Frequency analysis

· Machine learning


· Significant reduction of false positives up to 80%

· Increased accuracy

· Ability to run controlled feedback loops