A tailored course, built for your situation
AI-Driven Risk Modelling for Financial Services Practitioners
A practical, standards-aligned approach to modernizing capital adequacy workflows using machine learning and Basel III frameworks.
$199 one-time
24-hour access provisioning
30-day money-back guarantee
Hand-built implementation playbook
12 modules. 12 chapters per module. 144 chapters total.
12 modules, each with 12 chapters (144 chapters total), text-based, plus downloadable templates and a hand-built implementation playbook delivered alongside course access.
Most AI practitioners in finance can build models, but few can get them trusted, documented, and embedded in regulatory-grade risk processes.
The situation this course is for
Even strong technical work gets deprioritized when it lacks alignment with risk governance expectations or can't withstand senior review. Without clear pathways to formalize AI outputs in Basel-compliant terms, valuable research stays siloed.
Who this is for
AI Researcher at a regulated financial institution, focused on risk-aware model development and seeking greater influence in capital adequacy or compliance discussions.
Who this is not for
This is not for data scientists focused solely on marketing analytics or customer segmentation without risk or capital modelling context.
What you walk away with
- Design AI-enhanced risk models that align with Basel III documentation and governance expectations
- Produce model validation packages used by risk officers and compliance teams
- Lead internal conversations connecting AI innovation to capital adequacy frameworks
- Build reusable templates for model risk management that integrate with audit workflows
- Establish credibility as the go-to practitioner when new stress testing or capital planning initiatives launch
The 12 modules (with all 144 chapters)
Module 1. Foundations of AI in Regulatory Risk Modelling
Establish the connection between machine learning applications and Basel III's evolving expectations for model risk management in capital planning.
12 chapters in this module
- Understanding the role of AI in advanced IRB approaches
- How Basel III endgame changes impact model scope and frequency
- Distinguishing economic capital models from regulatory capital models
- Key differences between internal risk scores and regulatory inputs
- Mapping AI outputs to standardized capital ratio calculations
- Common pitfalls in model explainability for auditors
- Balancing innovation with supervisory scrutiny
- Integrating backtesting into AI-driven forecasting
- Defining model boundaries under BCBS 239 principles
- Documenting assumptions for internal model reviews
- Version control strategies for risk-sensitive models
- When to escalate model changes under governance policy
Module 2. Basel III Framework and Capital Adequacy Requirements
Break down the specific Basel III standards relevant to model design, including leverage ratio adjustments, capital buffers, and output floors.
12 chapters in this module
- Overview of the Basel III endgame capital framework
- Treatment of operational risk under the SMA approach
- Impact of the output floor on internal models
- Leverage ratio calibration with AI-adjusted exposures
- CVA capital requirements and model implications
- Capital conservation buffer triggers and forecasting
- Countercyclical buffer integration into stress testing
- Reporting requirements under Pillar 3 disclosures
- Jurisdictional variations in Basel III implementation
- Transition timelines for remaining national rollouts
- Interplay between CRR2 and US regulatory expectations
- Scenario planning for future Basel revisions
Module 3. AI Integration in Credit Risk Modelling
Adapt machine learning techniques to credit risk estimation while maintaining compliance with regulatory model validation standards.
12 chapters in this module
- Improving PD models with ensemble learning methods
- Integrating macroeconomic signals into retail portfolios
- Backtesting AI models against historical default cycles
- Feature engineering within SRP and NSFR constraints
- Stress testing performance under severe scenarios
- Handling data sparsity in low-default portfolios
- Model drift detection for long-term exposures
- Benchmarking against traditional scoring systems
- Transparency requirements for AI-based scoring
- Audit trail creation for model recalibrations
- Documentation standards for internal reviewers
- Governance handoffs between quants and risk teams
Module 4. Liquidity and Funding Risk with Machine Learning
Apply AI to liquidity forecasting and funding dependence metrics under LCR and NSFR frameworks.
12 chapters in this module
- Predictive modelling of deposit volatility under stress
- Enhancing LCR simulations with behavioural analytics
- Identifying hidden funding concentration risks
- Modelling contingent liquidity needs in interbank markets
- Incorporating client behaviour patterns into NSFR inputs
- Validating assumptions in cash flow projections
- Threshold monitoring for early warning systems
- Sensitivity analysis across funding tenors
- Stress testing wholesale funding dependence
- Backtesting AI forecasts against actual outflows
- Reporting liquidity risk aggregates to senior management
- Integrating AI outputs into ICAP processes
Module 5. Market Risk and AI-Enhanced VaR Models
Modernize Value-at-Risk calculations using machine learning while meeting FRTB requirements and audit readiness.
12 chapters in this module
- Improving tail risk estimation with deep learning
- Adapting VaR models to non-normal return distributions
- Integrating liquidity adjustments into market risk metrics
- Validating model outputs under stressed correlations
- Handling high-dimensional portfolios with dimensionality reduction
- Benchmarking AI-VaR against internal models
- Explainability requirements for senior reviewers
- Backtesting frequency and exception thresholds
- Stress scenario integration into daily metrics
- Model validation under SR11-7 guidelines
- Documentation for internal audit requests
- Escalation paths for model override events
Module 6. Operational Risk and Scenario Modelling
Leverage AI to identify, quantify, and project operational risk losses in line with SMA requirements.
12 chapters in this module
- Classifying operational loss events using NLP
- Predicting severity and frequency of cyber incidents
- Modelling third-party risk concentrations
- Integrating control effectiveness into loss estimates
- Scenario generation for rare but impactful events
- Backtesting operational risk forecasts
- Incorporating external loss databases
- Aggregating risk across business lines
- Thresholds for capital allocation decisions
- Documentation for model validation teams
- Stress testing under macroeconomic shocks
- Governance of model updates and recalibrations
Module 7. Model Risk Management Frameworks
Align AI model development with independent validation, ongoing monitoring, and audit expectations.
12 chapters in this module
- MRM lifecycle stages from development to retirement
- Roles and responsibilities in model governance
- Independent validation expectations for AI models
- Ongoing monitoring trigger design
- Model inventory management best practices
- Audit readiness for model documentation
- Version control and change management protocols
- Model performance thresholds and escalation
- Documentation standards for regulators
- Integrating challenger models
- Third-party model oversight
- Regulatory inspection response workflows
Module 8. Explainability and Interpretability in Regulated Environments
Meet supervisory expectations for transparency using techniques suited to deep learning and ensemble models.
12 chapters in this module
- SHAP values and their audit utility
- LIME for local interpretability
- Feature importance tracking over time
- Surrogate models for complex pipelines
- Partial dependence plots in risk contexts
- Global vs local explanation tradeoffs
- Documentation standards for explainability
- Handling non-linear interactions
- Validating explanation robustness
- Presenting results to non-technical reviewers
- Regulatory expectations for model justification
- Balancing performance with interpretability
Module 9. Stress Testing and Scenario Design
Generate credible, forward-looking scenarios using AI while preserving governance and auditability.
12 chapters in this module
- Defining scenario severity thresholds
- Integrating macroeconomic forecasts into models
- Generating extreme but plausible shocks
- Reverse stress testing using optimisation
- Backward-looking vs forward-looking design
- Incorporating climate risk scenarios
- Validating scenario plausibility with experts
- Documentation for internal review
- Reporting key assumptions to leadership
- Sensitivity analysis for capital projections
- Model adjustments under severe downturns
- Governance of scenario selection
Module 10. Regulatory Reporting and Disclosure
Structure model outputs to meet Pillar 3 and internal reporting requirements with clarity and precision.
12 chapters in this module
- Translating model results into regulatory formats
- Disclosure requirements for internal models
- Capital ratio reporting under Basel III
- Leverage ratio and buffer disclosures
- Risk-weighted asset breakdowns
- Model assumptions in public filings
- Internal dashboard design for risk committees
- Aggregation across business units
- Data lineage for audit trails
- Versioning of reported figures
- Escalation protocols for discrepancies
- Pre-review coordination with compliance
Module 11. Cross-Functional Alignment and Influence
Navigate stakeholder workflows between risk, compliance, finance, and senior leadership.
12 chapters in this module
- Translating technical work for risk officers
- Communicating model limitations to finance
- Aligning with compliance documentation standards
- Presenting to audit committees and reviewers
- Managing expectations on model certainty
- Facilitating peer review processes
- Handling challenge from internal validators
- Documenting rationale for model choices
- Escalation paths for governance disputes
- Integrating feedback into next iterations
- Building credibility over time
- Establishing norms across AI projects
Module 12. Sustained Implementation and Institutionalization
Ensure models remain relevant and trusted through change management and institutional memory.
12 chapters in this module
- Onboarding new team members to model logic
- Knowledge transfer protocols for quants
- Updating models with new regulations
- Revalidation schedules and triggers
- Handling leadership transitions
- Archiving deprecated models
- Version control for long-term compliance
- Training materials for ongoing use
- Integrating models into decision processes
- Feedback loops from end users
- Post-implementation review workflows
- Succession planning for model ownership
How this maps to your situation
- Model development lifecycle
- Regulatory capital planning
- Internal model validation
- Supervisory inspection readiness
Before vs. after
Before
Spending extra cycles defending or reworking AI models because they weren't built with risk governance in mind.
After
Confidently producing AI-driven risk models that meet Basel III expectations and gain quick approval from validators and auditors.
What's included with your purchase
- 12 modules with 12 chapters each (144 chapters total)
- Downloadable templates and worked examples for every module
- Hand-built implementation playbook delivered alongside course access
- 30-day money-back guarantee
Delivery and format
- Course and learning environment access provisioned within 24 hours of purchase
- Hand-built implementation playbook delivered alongside course access
Format: Text-based modules and chapters in the Art of Service learning environment, plus downloadable templates and worked examples for every chapter, plus the hand-built implementation playbook delivered alongside course access.
Time investment: Approximately 90 minutes per week over 12 weeks, with self-paced access and lifetime updates.
If nothing changes
Without alignment between AI innovation and risk governance, valuable research remains siloed, capital planning lags, and others, not you, lead the conversations that shape the firm’s future risk posture.
How this compares to the alternatives
Unlike generic AI courses or academic risk management programs, this course focuses specifically on the intersection of machine learning and Basel III implementation, giving you actionable templates, real-world validation patterns, and the recognition that comes from bridging two critical domains.
Frequently asked
Is this course technical or strategic?
It’s both, structured for AI practitioners who need to deliver technically sound models that also meet governance and regulatory expectations in practice.
How is the course structured?
12 modules, each containing 12 chapters (144 chapters total).
Will this help me get promoted?
It builds the kind of influence that leads to being included in high-impact risk and capital discussions, where visibility naturally follows.
$199 one-time. Approximately 90 minutes per week over 12 weeks, with self-paced access and lifetime updates..
Within 24 hours your account in the learning environment is provisioned and the tailored implementation playbook is delivered alongside it.
30-day money-back guarantee·
144 chapters·
Hand-built playbook included·
Account access within 24 hours