Install

Boost your operations with our modeling engine.

Datapred Install is a powerful machine learning suite that integrates
with your information systems to leverage the time series
your business is already generating.

Contact us

Times series unlimited

Datapred Install is the best machine learning suite for industrial time series on the market, period. Every aspect of time series modeling is optimized to give you maximum performance and durability - from data preprocessing to parallel computation. Built-in modules let you tackle most time-dependent challenges: predictions, simulations, scoring, allocation, clustering and anomaly detection.


Seamless integrations

Datapred Install is infrastructure- and system-agnostic:

  • You can install it in your datacenter, in a private cloud or a public cloud, at your convenience. Install comes with native Linux and Docker compatibility.
  • Install includes pre-built connectors for standard databases, and templates for connecting to non-standard databases and proprietary management systems (ERPs, CRMs, WMS…).
  • Datapred is an OSIsoft Application Partner and can easily link with your PI System.
  • Output formats are compatible with most data visualization tools.

Complete control

Coupling Datapred Explore and Datapred Install gives you complete control over your machine learning solution.

Periodically replicate your production data in a sandbox, and use Explore to safely test:

  • The contribution of additional data sources.
  • The performance of new predictive algorithms.
  • Refinements to your cost function.
  • Changes in your modeling target.
  • etc.

Then replicate back the successful improvements in Install. Done! Our expert data scientists can help you with this process if you lack the corresponding resources.

Features

  • Data sequentialization
  • Stationarization and filtering
  • Built-in models
  • Compatibility with ML libraries
  • Aggregation and stacking
  • Custom cost functions
  • Parallelization and distribution
  • Connectors
  • Graph structure
  • Performance monitoring
  • Checkpoints and backups
  • Continual improvement