The Promise of Deep Learning for AML
The key insight of deep learning for AML is that deep neural networks (DNNs) can generalize from training data to identify patterns in transactions that are indicative of fraud. That is, having been shown some patterns in real money laundering situations, DNNs can identify similar and modified patterns as also AML. This makes it harder for money launderers to make small changes in how they launder the money while coming under the radar of AML alerts (not triggering rules).
Dynamic Role-based Access Control
Manage Projects like Github Repositories and share Datasets like Dropbox
Hopsworks provides a new GDPR-compliant security model for managing sensitive data in a shared data platform. Hopsworks’ security model is built around Projects, which are analogous to Github repositories. A project contains datasets, users, and programs (code). Sensitive datasets can be sandboxed inside a project, and users can be assigned roles that prevent them from exporting data from the project.
Governance & Compliance
Hopsworks is built for Enterprises. Read the Product sheet how it provides: Hopsworks Product Sheet
- TLS-Based Security
- Feature Store to ensure data quality and clean training data for ML models
- Notebooks in ML Pipelines
- Conda environments & Pip Libraries in Air-gapped deployments