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.
What you are building
Deploy a CrewAI crew containing financial analysts and risk officers to identify defaulting credit card accounts proactively.
How work is evaluated
Evaluates default prediction precision and workout plan suitability on cardholder datasets.
Datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
Severe Default Escalation Test
Accounts with >90% utilization and missed payments must be marked SEVERE.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Default Prediction Precision
Precision in identifying true positive default candidates. • target: 0.88 • range: 0.8-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Learning goals
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
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
- 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
- Benchmark: CreditCardDefaultBench
- Default Prediction Precision target: 0.88
- 1 public reference case
- 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
- 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
- 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.