Data Prep
Append a data quality engine to your existing screening solution
Improve the accuracy and efficiency of your customer screening with data fit for AML compliance. FinScan Data Prep is a standalone module that connects to any AML solution to cleanse and format your data before screening.
Benefits
Improve productivity, reduce risk
Seamless integration
No need to replace your current AML platforms. Simply front-end your current screening solution with Data Prep to improve the quality of your screening results.
Optimize screening
Data Prep preprocesses your input data to resolve data quality and duplicate record issues, improving productivity and ensuring the highest integrity of all fields critical to screening accuracy.
Reduce risk
Accurately parse client data to identify and screen the true customer and entity names even when multiple names are included in the same field or improperly placed in address lines.
Profiling
Create a complete overview of your data to identify format inconsistencies and incomplete information
- Ensures the integrity of your data
- Uncovers gaps in data collection created during client onboarding
- Helps you effectively set up matching rules to reduce false positives
Cleansing
Parse and standardize customer data to prepare it for compliance screening
- Identifies hidden names in joint accounts and address lines to uncover potential sanctioned entities
- Flags dummy data and noise words so they don’t lead to false positives and unnecessary review efforts
- Separates address elements into the appropriate fields to identify sanctioned countries hidden in address lines
Deduplication
Identify and remove duplicate records across multiple data sources that feed into your compliance system
- Reduces the number of alerts by removing duplicates records
- Improves review productivity as analysts do not review redundant alerts
- Leads to the most optimal use of compliance resources and budget
Case study
Property and casualty insurance company
The organization had concerns regarding high volumes of false positives and inefficiencies in the case review process. Their analyst team often reported looking at the same alerts more than once. However, their primary concern was the risk of missing true suspicious activity due to errors in the data.
Challenge 1: Missing data
2.4MM individual records were missing Date of Birth (DoB), and the matching criteria heavily relied on exact DoB to identify matches.
Solution
Reliance on DoB matching to identify AML alerts was relaxed.
Challenge 2: Duplicate records
20% of the customer records used for screening were duplicates.
Solution
AML alert de-deduplication resulted in 17K fewer matches, saving 2,796 man-hours of wasted review time.
Challenge 3: Formatting issues
85K customer and entity records contained misplaced, missing, and hidden names in non-name fields.
Solution
Misplaced names were identified and screened, and 407 exact OFAC SDN matches were uncovered.