MathWorks Modelscape solution enables financial institutions to reduce the complexity of managing the lifecycle of financial models while improving model documentation, transparency, and compliance. By implementing the solution throughout the model lifecycle, users can:
- Use templated model workflows, automated documentation, and artifact linking
- Scale algorithms, models, and apps both horizontally and vertically
- Provide support for enterprise infrastructure, tooling, and languages such as Python, R, SAS, and MATLAB
- Track issues across the model lifecycle with full model lineage, issue, and usage reporting
- Comply with the principles provided in SR11-7, SS1/23, OSFI E-23, SS3/18, and other regulatory publications
The MathWorks Modelscape solution consists of six fully configurable components that support the management of data, models, and documents across the lifecycle. Each component supports integration with existing tools and infrastructure, from desktop to cloud. All lifecycle stages are synchronized through a centralized model inventory that tracks the full model lineage and use.
Manage models and modeling projects
- Provides a dashboard with a customizable executive level view into the models associated data and being able to run custom algorithms
- Deliver customizable and automated workflows across model lifecycle
- Web-centralized access to an inventory of all models in any language, data, dependencies, state, intermediate results, and full audit trail
Define and develop
- Explore, develop, back-test, and document models and methodologies
- Improve transparency, reproducibility, and reusability of models
- Auto-generate model documentation and reports
Ensure healthy models by reviewing business line data, building challenger models, and giving feedback and approving
- Provide a unified environment to test and validate models written in languages such as Python, MATLAB, and R
- Build challenger models using a comprehensive library of validated statistics, machine/deep learning, financial, risk, and econometric algorithms
- Provide workflows of communication through built-in interfaces to give feedback and model approval
- Generate automated model validation reports
Perform continuous integration and testing of model artifacts for ongoing quality assurance.
- Provide an environment for approved models to undergo pre-production user acceptance testing.
- Manage suites of automated and manual validation tests, with linking and traceability to development and reviews.
- Execute equivalence, performance, and coverage testing against in-production models against development specifications.
MathWorks Modelscape Test
Unified environment to execute and deploy models
- Perform language-agnostic deployment of models without refactoring or recoding models
- Host production models and scale to end users in a secure controlled environment
- Integrate with existing technology infrastructures and incorporate ModelOps best practices
- Manage the execution of multiple model versions across different environments
Monitor, report, and assess
- Get real-time model execution results using a configurable web dashboard
- Explore data segments and configure alerts and thresholds for automated monitoring
- Analyze model usage, behavior, and health to determine candidate models for retirement