Skip to main content
Back to challenges
Challenge

Develop a Credit Default Risk Early Warning Crew using CrewAI

Rising consumer credit card defaults necessitate proactive risk identification and automated restructuring plans. Build a CrewAI agent team that analyzes cardholder spending anomalies and macro signals to trigger early intervention strategies with 85% precision.

CybersecurityHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Deploy a CrewAI crew containing financial analysts and risk officers to identify defaulting credit card accounts proactively.

Delivery guide

How work is evaluated

Evaluation

Evaluates default prediction precision and workout plan suitability on cardholder datasets.

Datasets

Challenge datasets

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

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

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

Severe Default Escalation Test

Accounts with >90% utilization and missed payments must be marked SEVERE.

Binary check

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

Dimension 2

Default Prediction Precision

Precision in identifying true positive default candidates. • target: 0.88 • range: 0.8-1

Binary check

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

Learning goals

What you should walk away with

  • Design a CrewAI crew with defined roles: Macro Intelligence Agent, Spending Pattern Analyst, and Workout Strategy Advisor.

  • Ingest continuous credit card utilization trajectories and macroeconomic indicators.

  • Predict probability of default over 30-60-90 day windows.

  • Generate tailored credit limit adjustments and early workout plans.

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic UK consumer cardholder dataset detailing monthly spending, utilization, and default outcomes.

Challenge setup

Evaluates default prediction precision and workout plan suitability on cardholder datasets.

Challenge input

JSON with balance, credit_limit, minimum_payment_missed_count, spending_category_deltas

CrewAI

Orchestrates multi-agent role-playing workflows for credit assessment.

Evaluated output

JSON with risk_category ('LOW', 'MODERATE', 'SEVERE'), default_probability, action_plan

Evaluation checks
  • Accounts with >90% utilization and missed payments must be marked SEVERE.
  • Precision in identifying true positive default candidates. • target: 0.88 • range: 0.8-1
Configured evaluation evidence
  • Benchmark: CreditCardDefaultBench
  • Default Prediction Precision target: 0.88
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • CrewAI · Required
  • crewAI · Optional

Evaluation contract

  • Severe Default Escalation Test · Weight 1
  • Default Prediction Precision · Weight 1

Metrics

  • Default Prediction Precision · Target 0.88

Benchmarks

  • CreditCardDefaultBench
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON with balance, credit_limit, minimum_payment_missed_count, spending_category_deltas

    Output: JSON with risk_category ('LOW', 'MODERATE', 'SEVERE'), default_probability, action_plan

    Execution harness: Python

Evaluation tools

  • CrewAI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Develop a Credit Default Risk Early Warning Crew using CrewAI