Getting Started Guide

Everything you need to complete your Syntheticr trial

Trial Overview

What You Receive

  • One synthetic financial institution

  • Fixed dataset (approx. 5–7GB)

  • 24 months of transactions

  • Risk intelligence for first 18 months

  • Final 6 months unlabelled

Trial Limits

  • One alert submission

  • One PDF scorecard

  • 72-hour turnaround

  • Manual upload only

  • No API access

// Step 1 - Download Your Dataset

After activating your trial, you will receive a unique Open DeltaShare link by email.

The link is unique to you and remains active for 7 days

Dataset Characteristics

  • Size: 5–7GB

  • Structure: ISO20022 aligned

  • Components:

    • Entity profiles

    • Transactions

    • Risk intelligence

When joining tables, always include bank_id in your join conditions.

The dataset spans a time period of 24 months.

Risk intelligence is available for the first 18 months.

The final 6 months contains no risk intelligence to support unbiased evaluation.

The first 6 months act as a behavioural calibration period and does not contain alerts.

Risk intelligence includes true positives and false positives with realistic signal-to-noise ratios.

SAR filing does not automatically trigger exit.

Operational close-out windows may show post-exit transactions.

Counterparty completeness reflects institutional visibility limits.

These properties are deliberate. They should be considered when interpreting detection performance.

Structure and Design

Syntheticr is intentionally engineered to mirror operational AML environments.

Technical References

Before processing the dataset, you may wish to review the schema and table definitions:

View Technical Reference →

Download Data Dictionary (XLSX) →

Download Data Dictionary (CSV) →

// Step 2 - Identify Criminal Entities

Process Syntheticr exactly as you would production data.

You should generate alerts or entity-level detections using your existing rules, models, or hybrid approach.

The objective is to identify entities involved in money laundering activity within the synthetic institution.

This stage should replicate your normal operational configuration as closely as possible.

The dataset spans a time period of 24 months.

Risk intelligence is available for the first 18 months.

The final 6 months contains no risk intelligence to support unbiased evaluation.

The first 6 months act as a behavioural calibration period and does not contain alerts.

Risk intelligence includes true positives and false positives with realistic signal-to-noise ratios.

// Step 3 - Prepare and Upload Your Results

To request your scorecard, upload a CSV file containing a single required field:

entity_id

Example format:

entity_id

CUST-000234

CUST-004921

CUST-009115

Submission rules:

  • Only include entities you suspect of being involved in criminality.

  • Do not submit more than 30% of the total population.

  • Only one submission is permitted during the trial.

File format:

  • CSV

  • Single column of entity_id values

  • Header row recommended

Upload your file via the Syntheticr application:

https://app.syntheticr.ai

After submission:

Your file will be validated.

Ground-truth comparison will be performed.

Your PDF scorecard will be delivered via email within 72 hours.

Your Scorecard

Your scorecard provides an objective assessment of detection performance against known ground truth.

Overall Performance

This section summarises:

  • Entities submitted

  • Alert precision

  • Overall detection rate

  • Detection grade

Detection grades range from A* (95–100%) to E (<30%) and reflect entity-level detection capability.

This provides a clear baseline of current performance.

Interpreting Results

Performance by Dimension

The scorecard then evaluates detection across multiple dimensions:

  • Financial institution

  • Customer type (individual vs business)

  • Methodology (typology-level performance)

  • Transaction type

  • Risk intelligence (alerts, SARs, exits)

  • Network detection

Each section highlights strengths, gaps, and areas where detection may be inconsistent.

Detection grades range from A* (95–100%) to E (<30%) and reflect entity-level detection performance.

Precision measures how many of your alerts correctly identify criminal entities.

Detection rate measures how many criminal entities were successfully identified.

These should be interpreted together. High detection with low precision indicates over-alerting. High precision with low detection indicates under-detection.

The scorecard measures detection capability only. It does not assess investigation quality or SAR drafting.

After the Trial Period

This page describes the Trial, which includes:

  • One institution

  • One submission

  • One PDF scorecard

  • Manual upload

Paid plans extend this model.

Starter Plan

  • Ongoing monthly access

  • Regular scorecard submissions

  • PDF scorecards

Pro Plan

  • Multiple institutions

  • Detailed scorecards

  • Configurable data quality

  • API-based submission

At the end of your 30-day trial:

  • Card-based subscriptions convert automatically unless cancelled.

  • Invoice-based subscriptions receive an invoice per agreed terms.

For questions about upgrading or extending access, contact hello@syntheticr.ai.

Enterprise Plan

  • Ecosystem-level coverage

  • Machine-readable scorecards

  • Results API

  • Performance trend reporting

The trial demonstrates the methodology and scoring framework. Paid plans extend scope, automation, frequency, and depth.