Gracias por enviar su consulta! Uno de los miembros de nuestro equipo se pondrá en contacto con usted en breve.
Gracias por enviar su reserva! Uno de los miembros de nuestro equipo se pondrá en contacto con usted en breve.
Programa del Curso
AI in Credit Risk: Foundations and Opportunities
- Traditional vs AI-powered credit risk models
- Challenges in credit evaluation: bias, explainability, and fairness
- Real-world case studies in AI for lending
Data for Credit Scoring Models
- Sources: transactional, behavioral, and alternative data
- Data cleaning and feature engineering for lending decisions
- Handling class imbalance and data scarcity in risk prediction
Machine Learning for Credit Scoring
- Logistic regression, decision trees, and random forests
- Gradient boosting (LightGBM, XGBoost) for scoring accuracy
- Model training, validation, and tuning techniques
AI-Driven Lending Workflows
- Automating borrower segmentation and loan risk assessment
- AI-enhanced underwriting and approval processes
- Dynamic pricing and interest rate optimization using ML
Model Interpretability and Responsible AI
- Explaining predictions with SHAP and LIME
- Fairness in credit models: bias detection and mitigation
- Compliance with regulatory frameworks (e.g. ECOA, GDPR)
Generative AI in Lending Scenarios
- Using LLMs for application review and document analysis
- Prompt engineering for borrower communication and insights
- Synthetic data generation for model testing
Strategy and Governance for AI in Credit
- Building internal AI capabilities vs external solutions
- Model lifecycle management and governance best practices
- Future trends: real-time credit scoring, open banking integration
Summary and Next Steps
Requerimientos
- An understanding of credit risk fundamentals
- Experience with data analysis or business intelligence tools
- Familiarity with Python or willingness to learn basic syntax
Audience
- Lending managers
- Credit analysts
- Fintech innovators
14 Horas
