Help
  • FAQ
    • Introduction
    • Name Matching
      • Does Screena provide rules-based and/or fuzzy matching capabilities?
      • Does Screena have any machine learning or AI capabilities?
      • What are name cultures and how does Screena handle them?
      • How does Screena handle different scripts, diacritics, and transliteration?
      • How does Screena handle common names?
      • How does Screena handle inaccurate data?
      • What methods does Screena use to reduce false positives?
      • What is the percentage of false positives reduced with the methods used by Screena?
      • How does whitelisting work?
      • What differentiates pairwise name-matching between Screena One and Screena Plus?
      • How does secondary attributes-matching work?
      • Can Screena match beyond names and allow firms to blacklist identifiers or locations?
      • What is the difference between 'matchingNames' in screening responses and 'names' in 'targetData'?
    • Watchlists
      • Which lists are available out of the box?
      • Is Screena watchlist agnostic?
      • How is watchlist data loaded into Screena?
      • How frequently is data updated within Screena?
      • Do you provide proprietary watchlist data?
      • What sort of data (e.g., names, known aliases, known associates, etc) is used for name matching?
      • Does Screena support adverse media screening?
      • Do you provide information about whether a list entry is active, inactive or deceased?
      • Do you provide a URL link to the reference article for adverse media screening?
      • How is the data of third-party list providers conveyed to your name-screening API response?
      • Can I screen against specific sanction programs within a watchlist and not all of them?
      • What is the difference between the USA and the OFAC lists?
      • Is there a template to upload private lists into Screena?
      • How many records can I upload to my private watchlist?
      • Can I upload more than one private list?
      • How can I update my private list?
      • Why can't I find Politically Exposed Persons (PEPs) at regional level when I use Instant Search?
      • How do you monitor that watchlists are up to date and correctly uploaded to your platform?
    • Performance
      • Does Screena provide real-time screening capabilities?
      • What is the speed of screening?
      • How do you ensure horizontal and vertical scalability?
      • Does Screena support batch processing?
      • Do you have performance benchmarks?
    • Integration
      • Can clients configure the solution themselves or would they need support from you?
      • Do you partner with any other solutions/vendors?
      • Do you provide technology or solutions to support alert remediation investigation?
      • Can Screena be integrated within third-party platforms and systems?
      • How do you handle changes to your API data model?
    • Personalization
      • What options do I have to optimize my screening results?
      • What screening parameters can I configure to meet my risk appetite?
      • To which extent are the screening thresholds adjustable?
      • What is the difference between the algorithm value "ignore" and the option "nullMatch" set to false?
    • Hosting & Deployment
      • How can Screena be deployed?
      • How do you set resources per customer?
      • How do you segregate the data and configuration between customers?
      • How often does Screena release new versions?
      • How often are models re-trained and what does roll out to clients look like?
      • How do you handle High Availability?
      • What AWS regions do you operate as of now?
      • What operating systems and/or execution platforms are supported?
      • How do you provide bug fixes and distribution across clients?
    • Pricing & Support
      • What is your pricing model?
      • Can you clarify the difference between Screena One, Plus and Firm?
      • What additional modules are not included in your core product pricing package?
      • Do you charge for professional services and/or after-sales services?
      • Do you offer bespoke solutions to clients?
      • Can I test your solution for free?
      • What happens at the end of my trial period?
      • What are my payment options - credit card and/or invoicing?
      • What are your standard support & maintenance agreements?
      • Are there integration costs to work with Commercial-Off-The-Shelve (COTS) lists?
    • Security & Audit
      • Does Screena have security certifications?
      • What security measures do you apply?
      • How do you adhere to GDPR?
      • Does Screena provide versioning capabilities?
    • Tech Stack
      • What is your tech stack?
      • What programming language(s) is Screena written in?
      • What source and version control systems are used to manage development?
      • What testing tools do you use?
  • How To
    • Install Screena Portal
      • Preparing your system
      • Installing Screena Portal backend
      • Launching Screena Portal backend
      • Installing the web server
      • Configuring Screena Portal
    • Start Screena Portal
      • Starting PostgreSQL database
      • Starting Apache HTTP server
      • Starting Screena application
        • Start command
        • Restart command
        • Stop command
  • Release Notes
    • 2.1.17
    • 2.1.16
    • 2.1.15
    • 2.1.14
    • 2.1.13
    • 2.1.12
  • Legal
    • Terms & Policies
      • Website Terms of Use
      • Screena API Terms of Service
      • Screena API Data Policy
    • Privacy & Security
Powered by GitBook
On this page

Was this helpful?

  1. FAQ
  2. Name Matching

How does Screena handle inaccurate data?

PreviousHow does Screena handle common names?NextWhat methods does Screena use to reduce false positives?

Last updated 2 years ago

Was this helpful?

Before all, let’s clarify what inaccurate data is. Either human or machine errors can cause inaccurate data. It takes various forms: manual data mistakes (e.g., permuted name fields), missing data entry controls, unstructured/free format fields, missing or non-standardized information in databases, incompatible formats between data processing systems, etc.

Screena systematically controls the completeness and quality of imported data. For example, Screena ensures dates are always provided in accordance with the . Likewise, countries shall always be imported in .

When the original data is not compliant with those standards, Screena tries to resolve it using specific and . This normalization process harmonizes and transforms data into a format that makes attribute matching consistent. Normalization libraries are enriched with new synonyms or alternative spellings whenever an unknown or incompatible value is provided.

Screena’s tackle specific data quality issues such as typos, truncated names, out-of-order name elements, and split or concatenated names.

Screena data model also provides distinct fields to differentiate structured and unstructured information (e.g., parsed names vs. full names, structured addresses vs. free format addresses).

Distinct are actionable to handle all data quality nuances. For example, it is possible to use the parameter nullMatch and specify how a match should be handled when one attribute associated with an algorithm is either empty or not provided.

In other instances, inaccurate dates can be matched within the same year or decade.

Similarly, addresses can be matched within the same region or subregion based on the .

To achieve greater precision when screening free format fields, Screena applies advanced text analytics technics to detect distinct objects (named entities vs. addresses) within the same field and thus prevent irrelevant matches.

When it comes to name matching, Screena will call out generic machine learning models specifically trained with richer comprehensive datasets if no valid culture can be determined with high certainty.

ISO 8601 format
ISO 3166-alpha 2 format
normalization rules
libraries
rules-based algorithms
algorithm parameters
United Nations geoscheme