ZEMENTIS Predictive Analytics


Free Trial
Zementis Predictive Analytics
Try it for free


How Zementis works
Watch the video


We’re here to help
Contact us


Artificial Intelligence (AI), machine learning and predictive analytics will define the next generation of software. Zementis establishes a common, standards-based framework to deliver intelligent solutions across all industries and applications. With Zementis, organizations can harness the power of their data to rapidly deliver insights and support informed business decisions based on predictive analytics tools.

  • Quickly deploy, execute and manage predictive models that deliver instant insights your business can act on
  • Score data in real time or batch mode
  • Establish a common operational framework across all IT platforms

Enrich your data picture and leverage more accurate predictive models by leveraging huge data sets, real-time data, intermittent “bursts” of data and other data sources. Do massively parallel scoring for big data applications. There’s no environment too dynamic, no amount of data too large for open-standards-based Zementis.

See how Zementis works


Zementis gives your organization a single tool for predictive analytics. It is intuitive and easy-to-use, taking predictive analytics beyond the data science team so anyone in your enterprise can understand customer behavior, market dynamics, security risks and more—in real time.

Applications include:

  • Financial institutions—fraud & risk scoring, online transaction processing and advanced decision management
  • Internet of Things—sensor and device data processing, biometrics and IP network security
  • Sales & marketing—upselling/cross-selling, campaign optimization and making the next-best offer  

Our web-based console makes it easy for anyone to get the insights they need quickly and take action when it matters most.

Read the fact sheet


Zementis Predictive Analytics is based on open standards to draw on the innovation of a vast community of data scientists, statisticians, IT professionals and others who are experts at infusing quantitative techniques into sophisticated business decision making. Open standards also facilitate interoperability of predictive models across applications and vendors, so you can easily expand both your data-mining capacity and predictive modeling capabilities.

You'll use the Predictive Model Markup Language (PMML) standard to import and deploy predictive models. Zementis integrates with relational database systems and deploys natively on Hadoop® in conjunction with Hive™, Spark™ or Storm™. Additionally, you can quickly and cost effectively execute predictive analytics for IBM® z Systems® and transactional mainframe applications, such as COBOL, CICS®, Adabas and Natural.

More in our white paper


Software AG supports the open source community by maintaining several Python and R libraries for converting predictive models into PMML.

Nyoka is a Python library that provides comprehensive support for the latest PMML standard as well as extensions for data preprocessing, script execution and deep neural networks. Using Nyoka, you can export your predictive models from popular Python ML/DL frameworks into PMML. You can even create your own exporters for specialized/individual model types. Download Nyoka on GitHub now.

Use the R pmmlTransformations and the pmml packages to convert data transformations and predictive models from R into PMML. Download both packages via CRAN.

What you can do with Zementis

Quickly deploy, execute and integrate AI

Zementis Predictive Analytics is your platform for the agile deployment, integration and execution of predictive analytics. You gain a fast, scalable and secure way to deploy machine learning, AI and predictive models—ideal for organizations that rely on data to drive informed business decisions.

Score data in real time and batch mode

Zementis automates real-time and batch scoring for a wide range of predictive models and simplifies model deployment and IT system integration. Big data processing and streaming analytics are faster and cost efficient.

Scale your machine learning capabilities

Scale AI and machine learning capabilities across your business and operate effectively in complex, data-rich ecosystems, thanks to a robust architecture. Leverage huge data sets, real-time data, intermittent “bursts” of data and other data sources.

Establish a common framework across platforms

Based on open standards, Zementis facilitates interoperability of predictive models across different applications and vendors, helping you expand both your data science capacity and machine learning capabilities.

Key benefits

  • Accelerate time-to-market for intelligent decision making via AI, machine learning and predictive analytics
  • Reduce cost and complexity of operationalizing predictive models for big data
  • Easily adopt machine learning for real-time streaming analytics
  • Ensure scalability and reliability of machine learning model execution via uniform deployment platform
  • Ideal for highly dynamic and complex data environments
Benefits for data scientists
  • Exchange predictive models between different applications and vendors
  • Use any leading commercial and open-source data mining tool
  • Implement a wide range of machine learning and predictive algorithms
  • More readily incorporate artificial intelligence into ongoing business operations
  • Increase team productivity
Benefits for IT professionals
  • Simplify and accelerate the deployment of predictive models within the broader organization
  • Efficiently use your IT architecture by optimizing computational performance, capital expense and operating expense
  • Deploy machine learning capabilities in a vendor-neutral, cross-platform way
  • Integrate seamlessly with existing enterprise software and business processes
Benefits for business leaders
  • Rely on a common platform to make smarter decisions more effectively
  • Extend AI, machine learning and predictive use cases throughout your organization
  • Make faster, more accurate and consistent business decisions
  • Scale predictive analytics capabilities with the growth of your business
  • Enhance accountability for data-driven decisions


PMML support Zementis Predictive Analytics delivers a common predictive analytics strategy across the entire IT ecosystem. Fully supporting the Predictive Model Markup Language (PMML) industry standard for data mining applications, Zementis cements an efficient process for instant operational deployment, addressing the highest execution requirements for batch processing, in-memory computation and streaming data.
High-performance scoring

Count on a wide range of AI, machine learning and statistical algorithms for high-performance scoring, including:

  • Association rules
  • Decision trees for classification and regression
  • Neural network models: Back-propagation, radial-basis function and deep learning
  • Support vector machines for regression, binary and multi-class classification
  • Linear and logistic regression (binary and multinomial)
  • Naïve Bayes classifiers
  • General and generalized linear models
  • Cox regression models
  • Rule set models (flat decision trees)
  • Restricted Boltzmann machines
  • Clustering models: Distribution-based, center-cased and two-step clustering
  • Scorecards (including support for reason codes and point allocation for categorical, continuous and complex attributes)

Multiple Models: Model composition, segmentation, chaining, cascading and ensemble, including Random Forest Models and Boosted Trees

Support for data pre- and post-processing

Zementis Predictive Analytics also implements the definition of a data dictionary, missing, outlier and invalid values handling, and myriad other functions for implementing data pre- and post-processing functions, including:

  • Value mapping
  • Discretization
  • Normalization
  • Scaling
  • Logical and arithmetic operators
  • Conditional logic (IF-THEN-ELSE)
  • Built-in functions
  • Lookup tables
  • Business decisions and thresholds
  • JSON™
  • User-defined custom functions

Business needs

Increased speed, accuracy and consistency of business decisions Customer insight becomes real-time customer insight. AI, machine learning and predictive models deliver results based on more data points, increasing accuracy of business decisions. To become more agile in making smarter, data-driven business decisions, organizations must leverage the power of AI.
Scalability with business growth As the business grows, Zementis Predictive Analytics provides a cost-effective expansion path for your IT environment of choice. Rely on an enterprise-grade platform to integrate additional machine learning models, leverage more complex algorithms, and scale execution to millions of transactions without compromising agility.
Enhanced accountability for data-driven decisions Zementis is an enterprise-grade platform for managing complex machine learning and predictive models. That minimizes the need for custom code to ensure agility while reducing the risk for incorrect results. By using Zementis, you can minimize the movement of data across disparate systems to improve performance while enhancing data security.

Data mining platforms

Deep learning Deep learning is, without doubt, the hottest topic in machine learning and data science. It has fueled our imagination on what AI can achieve in the near future, from self-driving cars to personal digital assistants, medical diagnosis and robotics.

Read the fact sheet

IBM SPSS® Zementis is complimentary to IBM SPSS Modeler and Statistics and extends your modeling environment into the IT operational domain. It is compatible with Modeler and Statistics through PMML, the de facto standard for representing predictive models.

Read the fact sheet

KNIME® Once a model is exported from KNIME as a PMML file, that model can be directly deployed in Zementis Predictive Analytics for real-time or batch scoring.

Read the fact sheet

Python® Since Zementis Predictive Analytics is compatible with PMML, scikit-learn users benefit by gaining both extreme speed and extreme agility across the predictive model lifecycle.

Read the fact sheet

R From model development and testing to deployment and ongoing operation in a production environment, Zementis delivers more efficient data science to R users.

Read the fact sheet

SAP A model built in any of the SAP data mining tools and saved as a PMML file, can be deployed directly in Zementis Predictive Analytics for real-time or batch scoring.

Read the fact sheet

SAS® Zementis is compatible with SAS due to its use of PMML, the Predictive Model Markup Language.

Read the fact sheet

TIBCO® Statistica™ Zementis is complimentary to Statistica Modeler and Statistics, and it extends your modeling environment into the IT operational domain.

Read the fact sheet

SAP® is the registered trademark of SAP AG in Germany and in several other countries.

TensorFlow, the TensorFlow logo and any related marks are trademarks of Google Inc.




"Zementis Predictive Analytics helps our customers deploy, audit, integrate and execute predictive models with greater ease at a lower cost, which will ultimately help increase their profitability.”

James Reid | Senior VP, Core Software Engineering, Equifax


Support login