Skip to main content
Loading navigation
Back to challenges

Cross-Border Liquidity Optimization Engine for ISO 20022 Payments

Global banking institutions handle billions in cross-border settlements across fragmented liquidity corridors. Choosing the optimal settlement path requires dynamically balancing intermediary bank fees, foreign exchange spreads, transit latency, and Nostro account balance availability. In this challenge, you will implement an advanced payment routing engine using LangGraph and LangChain. The system will parse incoming ISO 20022 XML payment instructions, evaluate multi-hop settlement paths, and route payments through the lowest-friction corridor.

CybersecurityHosted by Vera
Sign in free to start

What you are building

Construct a LangGraph agent system to optimize cross-border payment corridors for ISO 20022 transactions.

How work is evaluated

Evaluation

Evaluates optimal path selection accuracy and cost savings on synthetic cross-border payments.

Datasets

Public datasets, plus the private datasets you have access to.

How submissions are scored

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

valid_corridor_selected

Ensures selected corridor exists in supported routing database

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

cost_reduction_percentage

Percentage savings compared to naive default SWIFT routing • target: 18.5 • range: 0-100

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

  • Design a stateful graph in LangGraph to manage settlement workflow transitions

  • Parse and validate complex `pacs.008` ISO 20022 XML fields

  • Implement multi-objective optimization for balancing fee, speed, and counterparty risk

  • Expose automated corridor selection telemetry via a REST API service

Resources

Dataset notes

Synthetic multi-currency payment transaction log containing ISO 20022 XML payloads and liquidity ledger updates.

Challenge setup

Evaluates optimal path selection accuracy and cost savings on synthetic cross-border payments.

Challenge input

ISO 20022 XML message and target performance priority

LangChain

Comprehensive ecosystem for language model application development.

LangGraph

Enables stateful multi-actor graph execution loops.

Evaluated output

JSON specifying optimal_corridor, total_cost_usd, and latency_estimate_minutes

Evaluation checks
  • Ensures selected corridor exists in supported routing database
  • Percentage savings compared to naive default SWIFT routing • target: 18.5 • range: 0-100
Configured evaluation evidence
  • Benchmark: FinPayments-Corridor-Bench
  • Cost Reduction Percentage target: 18.5
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Action Space
  • LangGraph · Required
  • Langchain · Optional
  • LangChain · Optional
Orchestration
  • LangGraph · Required
  • Langchain · Optional
  • LangChain · Optional

Evaluation contract

  • valid_corridor_selected · Weight 1
  • cost_reduction_percentage · Weight 1

Metrics

  • cost_reduction_percentage · Target 18.5

Benchmarks

  • FinPayments-Corridor-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: ISO 20022 XML message and target performance priority

    Output: JSON specifying optimal_corridor, total_cost_usd, and latency_estimate_minutes

    Execution harness: Python

Evaluation tools

  • LangChain · Agent Framework
  • LangGraph · Stateful Orchestration

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Cross-Border Liquidity Optimization Engine for ISO 20022 Payments