DataLabs & CleanRoom

Building and Running Models on Joint Data

In the end-to-end secure environment
Request a Demo
TRUSTED BY LARGEST BANKS, TELCO AND RETAILERS

One Platform for Starting and Streamlining Data Cooperation with any Partners

  • Partners’ data is connected using virtual DWH
  • Data is accessible via data catalogs
    and marketplaces. May be used for data discovery, data modeling, running models on shared data
    and activating results in communication channels
    and processes
  • Trusted execution environment is used for secure
    data calculations
  • Decentralized protocol – for managing metadata, rights and permissions, scripts approval, billing
    and other actions

Build ML Models, get Insights Working on Joint Data with Your Partners Without Sharing Data or Loosing Control Over it

1

Plug Your Data

Register it in the data catalog. Grant permissioned access to your partners
2

Order Partners’ Datasets

Using data marketplace
3

Develop and Train ML Models

In a protected datalabs VMs on depersonalized data
4

Industrialize Calculations

In Cleanroom on full scale data
5

Activate Results

In communications, processes and analytics

Plug your data

Register it in the data catalog. Grant permissioned access to your partners
  • Use the platform’s or your own databases
    (Virtual Data Warehouse)
  • Work with structured and semi-structured data
  • Define necessary distortion methods
  • Publish and describe your data
  • Grant access to the specific partners
    and cooperation cases

Order Partners’ Data

Using data marketplace
  • Pick the necessary partners’ data and make
    an order for it
  • Extract partners’ data for modeling into
    protected datalabs
  • Use direct P2P data exchange if agreed
    by the partners

Develop and train
ML Models

In a protected datalabs VMs on depersonalized data
  • Use familiar working environment
  • System automatically depersonalizes the data
    and applies distortion models
  • Discover partners’ data, upload additional data, build models
  • Publish results as scripts, audiences or reports

Industrialize Calculations

In CleanRoom on full scale data
  • Review and approve scripts to be executed full scale at your data
  • Put scripts for execution on schedule or evoke them using API
  • Control their execution using logs
  • Avoid any disputes as logs stored
    at the immutable ledger

Activate Results

In communications, processes and analytics
  • Provide insights on the joint data to your partners with secure BI
  • Use API to integrate calculations into
    your processes
  • Use the resulting audiences
    in the communication engine
  • Create analytics in BI or add other features
    to your database, such as underwriting scores
  • Activate audience data
    in communication platforms

Trusted Environment for Working
with Any Parties

  • Do calculations with two
    or more parties
  • Use decentralized smart contracts to manage access and restrictions
  • Have full control over
    all operations using
    immutable ledger

Variability of Calculations

  • Use familiar programming languages: Python, R, PySparc, Scala, Java and others
  • Work with structured
    and semi-structured data
  • Run any number
    of simultaneous calculations

Security and Privacy by Design

  • Hardware based encryption using Intel SGX
  • Build models on depersonalized datasets
    in a protected environment
  • Train models in datalabs or fully confidentially in cleanrooms
  • Execute models in cleanrooms
  • Have your personal data protected and invisible
Using Intel SGX has allowed us to build a platform that can securely and privately process data from a variety of partners. This allows us to all collaborate better and create more effective advertising campaigns for customers. Our team is extremely excited about the upcoming enhancements to Intel SGX that will allow the secure enclaves to handle even more data, meaning we can further scale our data management platform.
The Aggregion solution will allow us to unite efforts to find the most effective methods of working with a joint client base within the framework of absolute security and confidentiality of both commercially significant information and complete protection of personal data.

Enterprise Readiness

Easy Cooperation Among Enterprises

  • Use enterprise decentralized protocols & Intel SGX
  • Control the processes
    with the central
    administration console
  • Manage your applications
    on Kubernetes
  • Stay safe with authentication protocols (Oath, AD)

Flexible Deployment Options

  • Decide on the side to host your data lab and the enclave
    to perform calculations
  • Choose between cloud
    or on-premise infrastructure

Ready to Give Aggregion a Try?

Realize Your Data Cooperation Opportunities
Contact Us