ORCHESTRATION/TRANSFORMATION

Distributed Computational Graph

Orchestration tool for complex data transformation workflows

Complex Workflow Orchestration for Advanced Decision Platforms

Data Management and Integration Optimization Workflows

Planning and Simulation Workflows for Business Intelligence

Embrace Complexity with Ease

Fractal's Distributed Computational Graph (DCG) is a state-of-the-art orchestration service that functions as the nucleus of Fractal OS. It coordinates activities ranging from simple notification messaging to complex workflows like identifying and alerting on anomalous behavior in near real-time or running a sophisticated simulation based on streaming sensor feeds.

These highly customizable orchestrations typically involve a series of automated activities driven by machine learning (ML) algorithms and distributed across clusters of nodes for fault tolerance and high-throughput, parallel processing. DCG enforces comprehensive workflow integrity by triggering subsequent tasks only when all criteria are met, and it further protects against silent failures by allowing you to configure retry attempts or other automations if a failure does occur. Workflow outcomes can then be used to enrich new data, effectively driving optimization across the enterprise by creating a feedback loop of continuous improvement for almost any process.

By abstracting away the end-to-end complexity of these sophisticated data management and analytic workflows, DCG finally frees you to focus on the things machines can’t do.

DOCUMENTATION

Example Use Cases

Complex Workflow Orchestration for Decision Platforms

Advanced Cyber Decision Platform (ACDP)

A single, unified platform to correlate and contextualize security data, reveal and manage cyber risk, elevate human talent, and drive continuous improvement of cybersecurity posture across the enterprise.

Advanced Insurance Decision Platform (AIDP)

A cloud-based decision-support system designed to help insurance brokers, (re)insurers, and insurance-linked securities (ILS) market participants to understand, model, manage, and transfer risk in a way that maximizes profitability over a long-term-horizon.

Quantitative Trading Decision Platform (QTDP)

A high-performant, multi-asset, multi-strategy trading platform designed for data-driven, human-machine collaboration, leveraging a multi-layered, model-based approach in which discrete learning algorithms compete to deliver optimal returns.

Data Management and Analytic Optimization Workflows

Advanced Data Management (ADM)

A suite of tools for cleansing, normalizing, organizing, enriching, augmenting, and curating text data in almost any format for context-rich analytics and simulation modeling capabilities driven by machine learning algorithms.

Advanced Model Management (AMM)

A workflow that supports the the creation, administration, and operation of parameter-driven models and machine learning algorithms, including model health monitoring, model bias and performance reporting, model cross-validation, hyper-parameter search and optimization, and parameterized model tuning.

Digital Replica Generation

A set of integrated workflows that enable continuous ingestion, correlation, and enrichment of data from widely diverse sources for Knowledge Base Construction (KBC) and the creation of a Cyber-Physical Graph (CPG) that maps all entities within a real-world system along with their relationships and interactions over time, providing a Digital Replica that can be used to explore "what-if" scenarios without impacting production systems.

Planning and Simulation Workflows for Business Intelligence

Decision Support

A high-level workflow that automates iterative runs of simulations using parameterized FractalSim, MMOGS, and Automated Planning templates to recommend optimal decision support for complex business scenarios that typically involve RoI-based analytics.

Risk Analysis & Management

A development environment that allows you to analyze and explore options to economically minimize enterprise-wide risk using dynamically automated DCG pipelines, particularly leveraging Automated Planning for well-specified risks, and FractalSim and MMOGS for modeling of risks that are less predictive.

Experimental Design & Management

A web-based tool for rapid design of workflows that use other Fractal OS components to gain insight from data analysis, typcially based on ad hoc queries that can be saved for future experimentation or automation and include rich, customizable visualization capabilities.

Features

Unprecedented Flexibility

Easily integrate applications and services to build complex workflows and automations in minutes.

Simple Usability

Guided component configuration and an intuitive drag-and-drop workflow builder UI are provided in an interactive web portal.

Elevation of Human Talent

Automation of mundane business processes frees up human talent to focus on the things machines can't do.

Improved Accuracy

Automated, data-enriched workflows promote the context to promote the right result or decision the first time.

Increased Consistency

Identical processing based on customizable conditions and triggers reduces output variation.

Greater Productivity

Tedious and repetitive tasks can be performed by virtual full-time employees working 24/7/365.

Adjustably Autonomous

The degree of automation associated with any workflow can be adjusted dynamically to accommodate human intervention as needed.

Dynamic Scalability

Easily add or remove workflow automations or participating components to achieve new integrations or outcomes.

Compliance and Accountability

Automated logging provides comprehensive audit trail of outcomes associated with every step of a workflow.

Fault Tolerant

Distributed, cloud-based deployment ensures high availability of data and services to meet the most demanding SLAs.

Continuous Monitoring

Automatic notifications and interventions are easily implemented to protect against silent failures and ensure timely response.