Match scoring controls how broadly or narrowly Minerva keeps potential screening matches as they move through candidate retrieval, entity resolution, and final result filtering.
Access: Requires the Admin role or above. In the
sidebar, go to Administration > Configuration,
then open Match scoring under Screening behaviours.
Use this guide when you need to:
- understand what the Match scoring page controls
- choose between the built-in scoring presets
- tune pre-resolution and post-resolution score thresholds by workflow
- understand how criteria match scores and score labels should be interpreted
- decide how strict the News geography filter should be before adverse-media data reaches the Minerva engine
- review, audit, or roll back match scoring changes
Balanced is the default Match Scoring configuration for every
organization. It preserves Minerva’s legacy scoring posture unless your
organization has explicitly changed the settings.
Match scoring changes affect which candidates analysts see. Tune in small
increments, use detailed change description notes in the updates, and compare
review volume and missed-risk sensitivity before moving further away from
Balanced.
How Match Scoring Works
Every screening result passes through three broad stages:
- Candidate retrieval: Minerva gathers source records from the
selected feeds.
- Pre-resolution scoring: each source candidate is scored
against the searched subject before entity resolution.
- Post-resolution scoring: Minerva clusters likely duplicate
source records, scores the resolved candidate, and filters the final returned
result set.
The Match Scoring configuration controls the second and third stages through:
- pre-resolution thresholds for each feed:
Sanctions, PEP, and News
- one post-resolution threshold for the workflow
- the News data filter, which controls how subject geography is used when retrieving news articles before internal scoring
The configuration is workflow-specific. Minerva currently separates:
| Workflow | What it covers | Default Balanced posture |
|---|
| Onboarding | Profile onboarding and first-pass screening workflows. | Stricter final threshold of 0.85. |
| Ongoing monitoring | Repeated monitoring screens for existing profiles. | Stricter final threshold of 0.85. |
| Direct API calls | API-driven screening submissions. | Broader final threshold of 0.70. |
| Risk assessments | One-off risk-assessment searches in the app. | Broader final threshold of 0.70. |
Understanding Scores
Minerva uses normalized match scores from 0.00 to 1.00.
- 1.00 means the compared values are effectively exact matches.
- Values closer to 1.00 are stronger matches.
- Values closer to 0.00 are weaker matches.
- A threshold is the minimum score required to keep the candidate at that stage.
In result details and API responses, field-level criteria match labels are interpreted as:
| Label | Score range | Meaning |
|---|
| Exact | 0.98 and above | The field is effectively exact. |
| Close | 0.85 to below 0.98 | The field is strongly similar, but not exact. |
| Loose | 0.75 to below 0.85 | The field is a weaker fuzzy match. |
| None | Below 0.75 | The field does not provide meaningful match evidence. |
Pre-Resolution vs Post-Resolution Thresholds
Pre-resolution and post-resolution thresholds answer different questions.
Pre-Resolution Thresholds
Pre-resolution thresholds decide whether a raw feed candidate is strong enough to continue into entity resolution.
Each workflow has separate pre-resolution thresholds for:
Raise a pre-resolution threshold when a feed is sending too many weak candidates into the pipeline. Lower it when analysts are missing plausible source records before entity resolution has a chance to group and enrich them.
Example: raising the News pre-resolution threshold for Ongoing monitoring makes Minerva reject weaker adverse-media candidate records earlier, before they can be clustered with other source records.
Post-Resolution Threshold
The post-resolution threshold is the final score a resolved candidate must meet before it remains in the returned result set.
Post-resolution scoring happens after Minerva has clustered likely duplicate or related source records for the same candidate. This final score is what controls the analyst-visible result list after entity resolution.
Raise a post-resolution threshold when resolved matches are still too broad after clustering. Lower it when entity resolution is correctly grouping evidence, but the final result list is hiding candidates your team wants to review.
If weak records are obviously not related to the searched subject, tune the
feed-specific pre-resolution threshold first. If records look related before
entity resolution but disappear after final scoring, tune the post-resolution
threshold.
Built-In Presets
Minerva includes three built-in presets. Built-in presets stay fixed, and organization presets can be created from a custom draft.
Balanced
Balanced preserves the legacy scoring defaults and strict News geography behavior.
Use Balanced when you want Minerva’s standard screening posture and do not have evidence that a specific workflow needs broader or narrower matching.
| Workflow | Sanctions pre | PEP pre | News pre | Post |
|---|
| Onboarding | 0.85 | 0.85 | 0.85 | 0.85 |
| Ongoing monitoring | 0.85 | 0.85 | 0.85 | 0.85 |
| Direct API calls | 0.75 | 0.75 | 0.70 | 0.70 |
| Risk assessments | 0.75 | 0.75 | 0.70 | 0.70 |
Narrow
Narrow raises thresholds and keeps strict News geography filtering.
Use Narrow when review volume is too high and your program can tolerate less borderline recall in exchange for fewer weaker matches.
| Workflow | Sanctions pre | PEP pre | News pre | Post |
|---|
| Onboarding | 0.90 | 0.90 | 0.90 | 0.90 |
| Ongoing monitoring | 0.90 | 0.90 | 0.90 | 0.90 |
| Direct API calls | 0.85 | 0.85 | 0.80 | 0.80 |
| Risk assessments | 0.85 | 0.85 | 0.80 | 0.80 |
Wide
Wide lowers thresholds and broadens News geography filtering.
Use Wide for calibration reviews, higher-risk cohorts, or workflows where the cost of missing a plausible match is higher than the cost of reviewing additional candidates.
| Workflow | Sanctions pre | PEP pre | News pre | Post |
|---|
| Onboarding | 0.75 | 0.75 | 0.75 | 0.75 |
| Ongoing monitoring | 0.75 | 0.75 | 0.75 | 0.75 |
| Direct API calls | 0.65 | 0.65 | 0.60 | 0.60 |
| Risk assessments | 0.65 | 0.65 | 0.60 | 0.60 |
News Geography Bias
The News data filter controls the geography bias used before news articles enter the Minerva engine.
This setting affects upstream article retrieval. It changes the article pool that Minerva asks the News source to return. The adverse-media model and downstream scoring can only evaluate articles that were retrieved, so this setting can materially bias what data reaches the engine.
| Setting | Retrieval behavior | Data bias introduced |
|---|
| Strict | Searches the subject name in article header or summary and applies city and state terms when available. | Biases toward local or regional articles that match supplied city/state context. This usually reduces common-name noise but may miss national, international, or body-only mentions. |
| Broad | Searches the subject name in header, summary, or body and adds a broader geography clause using city, state, or country when available. | Biases toward the supplied country or region while allowing more article text matches. This increases recall and can surface broader coverage, but it can also increase common-name noise. |
| None | Searches the subject name in header, summary, or body without geography terms. | Applies the least geography bias. This maximizes recall across the news corpus and is most likely to increase unrelated common-name articles. |
Request-level API parameters still override the tenant News data filter. For
example, an API request that explicitly sets a News geography bias value takes
precedence for that request.
Request-Level Overrides
Match scoring is the organization default. It applies when the screening request does not provide an explicit override.
Core screening logic gives request-level values precedence over tenant configuration. In practice:
- a feed-level
match_threshold overrides feed-stage thresholds for that feed
- a feed-level
pre_resolution_match_threshold overrides the tenant pre-resolution threshold for that feed
- a global
match_threshold acts as a legacy override and takes precedence over post-resolution threshold defaults
- a global
post_resolution_match_threshold overrides the tenant post-resolution threshold
- global or News feed-level
news_geography_bias overrides the tenant News data filter
This is important for API users. A tenant can keep a stable organization default while a specific API integration or investigation flow requests a narrower or wider threshold for a single submission.
Recommended Tuning Approach
Use this sequence when calibrating match scoring:
- Start from Balanced and collect examples of false positives, plausible missed matches, and high-volume review cohorts.
- Tune one workflow at a time. Onboarding, monitoring, API, and risk assessment often have different tolerance for review volume.
- Tune one feed at a time for pre-resolution thresholds. Sanctions, PEP, and News have different data density and false-positive patterns.
- Adjust pre-resolution thresholds before post-resolution thresholds when the issue is feed-specific noise.
- Adjust post-resolution thresholds when entity resolution is grouping candidates correctly but the final result set is too broad or too narrow.
- Be deliberate with News geography bias. Moving from Strict to Broad or None changes the upstream article pool, not only the final score filter.
- Save a clear change description so history shows why the calibration was deployed.
- Use history and rollback if the change moves review volume or recall in the wrong direction.
General tuning guidance:
- higher thresholds are stricter and usually reduce analyst-visible matches
- lower thresholds are broader and usually increase recall and review volume
- lowering News thresholds and setting geography bias to Broad or None at the same time can create a large increase in adverse-media candidates
- monitoring changes should be made carefully because they can change recurring alert volume across an existing profile population
- direct API changes should be coordinated with API consumers, especially if those consumers already submit request-level overrides
Reviewing And Confirming Changes
When you click Review changes, Minerva shows a grouped confirmation view before anything is saved.
The review dialog shows:
- the number of changes and sections affected
- the selected preset change, if applicable
- each workflow with changed pre-resolution thresholds
- the changed post-resolution threshold
- the changed News data filter
- an optional Change Description field
Use the change description to capture the reason for the calibration, such as a false-positive review, a model calibration review, a high-risk cohort exception, or a post-launch monitoring adjustment.
Deployment History And Rollback
The Match Scoring page includes a quick History drawer so you can preview recent deployments without leaving the configuration page.
Use the drawer to:
- see the current live deployment first
- review prior threshold and News geography changes
- preview an older deployment on the main page
- open the full audit history page
Rollback restores a previous deployment by writing a new history entry. It does not delete prior history.
The full history page includes:
- Changed: when the configuration was saved or rolled back
- Action: whether the event was an update or rollback
- Summary: the key threshold or News filter changes
- Changed by: the user who performed the change
- Actions: rollback entry points for older deployments
