Skip to main content
Didit’s AML Screening provides real-time risk detection by screening users against global watchlists and databases. The solution combines advanced data matching with AI-powered risk assessment to ensure regulatory compliance while maintaining a smooth user experience.

​
Key Concepts: Match Score vs Risk Score

Didit uses a two-score system for AML screening:

​
Match Score (Identity Confidence)

  • Question: Is this match the same person we’re screening?
  • Factors: Name similarity, Date of Birth, Country/Nationality, Document Number
  • Purpose: Classifies match as False Positive or Unreviewed (Possible Match)
  • Threshold: Match Score Threshold (default: 93)

​
Risk Score (Entity Risk Level)

  • Question: How risky is this entity if it’s a true match?
  • Factors: Country risk, Category (PEP/Sanctions/etc.), Criminal records
  • Purpose: Determines the final AML status (Approved/In Review/Declined)
  • Thresholds: Approve Threshold (default: 80) and Review Threshold (default: 100)
┌─────────────────────────────────────────────────────────────────────────────┐
│                           AML SCREENING FLOW                                │
├─────────────────────────────────────────────────────────────────────────────┤
│                                                                             │
│  STEP 1: Screen against watchlists                                          │
│     └── Returns potential matches (match score ≥ 75% included)              │
│                                                                             │
│  STEP 2: For each match, calculate MATCH SCORE                              │
│     └── Match Score = (Name × W1) + (DOB × W2) + (Country × W3)             │
│                                                                             │
│  STEP 3: Classify match by match score                                      │
│     ├── Match Score < 93 → FALSE POSITIVE (excluded from risk)              │
│     └── Match Score ≥ 93 → UNREVIEWED (included in risk)                    │
│                                                                             │
│  STEP 4: For unreviewed matches, calculate RISK SCORE                       │
│     └── Risk Score = (Country × 30%) + (Category × 50%) + (Criminal × 20%)  │
│                                                                             │
│  STEP 5: Determine AML STATUS (highest risk score among non-FP matches)     │
│     ├── Risk Score < 86 → APPROVED                                          │
│     ├── 86 ≤ Risk Score ≤ 100 → IN REVIEW                                   │
│     └── Risk Score > 100 → DECLINED                                         │
│                                                                             │
└─────────────────────────────────────────────────────────────────────────────┘

​
Match Review Statuses

Each AML match is assigned a review status based on its match score:
StatusDescriptionWhen Assigned
False PositiveMatch is likely NOT the same personMatch score < threshold (auto-assigned)
UnreviewedMatch is a possible match requiring reviewMatch score ≥ threshold (auto-assigned)
Confirmed MatchMatch has been verified as the same personManually set by compliance officer
InconclusiveUnable to determine if match is the same personManually set by compliance officer

​
Tip: You can change a match review status in the Console by viewing the AML overview or clicking on a specific match to see its details.

​
Key Features

​
1. Comprehensive Data Extraction

  • Accurate Extraction: Extract data from user-provided information or identity documents using advanced OCR technology.
  • Fuzzy Logic: Account for name variations and misspellings to ensure comprehensive data capture.

​
2. Extensive Watchlist Coverage

Screen against multiple categories including:
  • Sanctions Lists: From government and international bodies.
  • Politically Exposed Persons (PEPs): Individuals with prominent public functions.
  • Criminal Records: Including global and local criminal databases.
  • Adverse Media Mentions: News articles and reports on financial crimes and other risks.
  • Custom Watchlists: Configurable based on specific client requirements.

​
3. Advanced Matching Algorithms

  • Fuzzy Matching: Catch slight variations in names or details to ensure accurate matching.
  • Multiple Data Points: Utilize name, date of birth, nationality, and other identifiers for thorough screening.
  • Golden Key Logic: Document number matching that can override scores for definitive identification.

​
4. Two-Score Risk Assessment

Each match receives TWO scores:
ScorePurposeClassification
Match Score (0-100)Is this the same person?False Positive vs Unreviewed
Risk Score (0-100)How risky is this entity?Determines final AML status
Match Review Status (based on Match Score):
  • False Positive: Match score below threshold - likely NOT the same person
  • Unreviewed: Match score at or above threshold - requires review
Final AML Status (based on highest Risk Score among non-false-positive matches):
  • Approved: All unreviewed matches have low risk scores
  • In Review: At least one unreviewed match has medium-high risk score
  • Declined: At least one unreviewed match has very high risk score

​
5. Detailed Adverse Media Screening

Screen against a wide range of adverse media categories, including:
  • Financial Crimes: Money laundering, embezzlement, and more.
  • Violent Crimes: Assault, murder, and related offenses.
  • Terrorism: Involvement in or support for terrorist activities.
  • Narcotics: Drug trafficking and related crimes.
  • Fraud: Various types of fraud and deceptive practices.
  • Regulatory Violations: Breaches of regulatory compliance requirements.

​
6. Customizable Screening Parameters

  • Adjustable Sensitivity: Configure the screening sensitivity based on your organization’s risk appetite.
  • Customizable Watchlists: Select which watchlists and categories to include in the screening process to meet specific requirements.

​
Configurable Thresholds

You can customize security levels by setting different thresholds: Match Score Configuration:
SettingDefaultDescription
Match Score Threshold93Matches below this are False Positives, at or above are Unreviewed
Name Weight60Weight for name in match score
DOB Weight25Weight for DOB in match score
Country Weight15Weight for country in match score
Risk Score Thresholds (Final Status):
SettingDefaultDescription
Approve Threshold80Risk scores below = Approved
Review Threshold100Risk scores above = Declined; between = In Review
These thresholds can be adjusted based on your risk tolerance and security requirements.

​
How It Works

Our AML Screening process efficiently identifies potential risks while minimizing delays for legitimate users.

Data Extraction

The system extracts relevant information from either user-provided data or uploaded identity documents.
InputMethod
Identity documentsAdvanced OCR technology for accurate data extraction
User-provided dataDirect input (name, DOB, nationality, document number)
Fuzzy logicAccounts for name variations and misspellings

Watchlist Screening

The extracted data is cross-checked against 1,300+ global watchlists and databases in real time:
  • Sanctions Lists — Government and international bodies (OFAC, EU, UN, etc.)
  • Politically Exposed Persons (PEPs) — Individuals with prominent public functions
  • Criminal Records — Global and local criminal databases
  • Adverse Media — News articles and reports on financial crimes
  • Custom Watchlists — Configurable based on your requirements

Match Score Calculation

For each potential match, the system calculates an identity confidence score — how likely it is the same person.
FactorDefault WeightDescription
Name similarity60%Fuzzy matching accounting for variations
Date of Birth25%Exact or partial DOB comparison
Country/Nationality15%Country of origin comparison
  • Match Score below threshold (default: 93) → classified as False Positive
  • Match Score at or above threshold → classified as Unreviewed (possible match)
  • Golden Key: Document number match can override to 100% for definitive identification

Risk Score Calculation

For non-false-positive matches, the system calculates the entity’s risk level:
FactorWeightDescription
Category50%PEP level, sanctions type, criminal severity
Country risk30%Risk rating of associated countries
Criminal records20%Presence and severity of criminal history

Final Status Determination

Based on the highest risk score among all non-false-positive matches:
Risk ScoreStatusAction
Below approve thresholdApprovedAuto-cleared, no credible risk
Between thresholdsIn ReviewFlagged for manual compliance review
Above review thresholdDeclinedHigh risk, automatic rejection
If all matches are false positives, the result is Approved (no credible matches found).

Result Generation

A detailed report is generated with full transparency:
  • Each match’s match score and risk score with breakdowns
  • Match classification (False Positive vs. Unreviewed vs. Confirmed)
  • Source database and category details for every hit
  • Results delivered via API response, webhook, or Business Console
  • Automatic decisioning based on your configured risk score thresholds