IBM Machine Learning for z/OS® (MLz) is an enterprise machine learning solution that runs on IBM Z®. It provides a web user interface (UI), various APIs, and a web administration dashboard with a powerful suite of easy-to-use tools for model development and deployment, user management, and system administration.
Infuse machine learning and deep learning models with your z/OS applications and deliver real-time business insights at scale. Easily import, deploy, and monitor models to achieve value from every transaction, and drive new outcomes for your enterprise while maintaining operational SLAs.
For greater flexibility, Machine Learning for z/OS includes two editions:
All IBM Machine Learning for IBM z/OS editions can run as a standalone solution or infuse it into your enterprise AI capability as a scalable platform.
Visualized explanations of AI inferences can be natively accessed in MLz
Leverage the unprecedented power of IBM z16™ and the Telum™ AIU. Process up to 228K z/OS CICS® credit card transactions per second with 6 ms response time1, each with an in-transaction fraud detection inference operation using a Deep Learning Model.
Co-locate applications with inferencing requests to help minimize delays caused by network latency. This delivers up to 20x lower response time and up to 19x higher throughput versus sending the same inferencing requests to a compared x86 cloud server with 60ms average network latency.2
Leverage trustworthy AI capabilities like explainability and monitor your models in real time for drift, fairness or bias detection and robustness to develop and deploy your AI models on z/OS for mission-critical workloads with confidence.
With the update to version 3.1, MLz is offering more flexibility to clients and solution providers with the introduction of 2 new offerings: Enterprise Edition and Core Edition.
Enhanced edition that delivers improved scoring performance, a new version of Spark and Python machine learning runtimes, and includes GUI-guided configuration tool and more.
A lightweight version of WMLz providing the essential services that are REST-API-based for machine learning operations including online scoring capabilities on IBM Z.
UI (for model management & deployment, admin dashboard)
Repository database (built-in & Db2 for z/OS)
AI Model training tool (integrated Jupyter Notebook)
Spark ML runtime
Python ML runtime
SparkML & PMML scoring runtime
Python & ONNX scoring runtime
Inference Services – RESTful interface
Inference services – native interface
Integrated in-transaction scoring (CICS & IMS apps)
Machine Learning for z/OS uses both IBM proprietary and open source technologies and requires prerequisite hardware and software.
Leverage the best of the mainframe and the innovation of the cloud.
Proactively identify operational issues and avoid costly incidents by detecting anomalies in both log and metric data.
Access a library of relevant open source software to support today's artificial intelligence (AI) and machine learning (ML) workloads.
Leverage a secure and scalable operating system for running mission-critical applications.
Enhance availability, security and resiliency while improving performance and business results.
Get high-speed data analysis for real-time insight under the control and security of IBM Z.
Learn how AI enhances usability, improves operational performance and maintains the health of IBM® Db2® systems.
Explore Machine Learning for IBM z/OS. Schedule a no-cost 30-minute meeting with an IBM Z representative.
1 DISCLAIMER: Performance result is extrapolated from IBM internal tests running a CICS credit card transaction workload with inference operations on an IBM z16. A z/OS V2R4 LPAR configured with 6 CPs and 256 GB of memory was used. Inferencing was done with Machine Learning for z/OS 2.4 running on Websphere Application Server Liberty 22.214.171.124, using a synthetic credit card fraud detection model (https://github.com/IBM/ai-on-z-fraud-detection) and the Integrated Accelerator for AI. Server-side batching was enabled on Machine Learning for z/OS with a size of 8 inference operations. The benchmark was executed with 48 threads performing inference operations. Results represent a fully configured IBM z16 with 200 CPs and 40 TB storage. Results may vary.
2 DISCLAIMER: Performance results are based on an IBM internal CICS OLTP credit card workload with in-transaction fraud detection running on IBM z16. Measurements were done with and without the Integrated Accelerator for AI. A z/OS V2R4 LPAR configured with 12 CPs, 24 zIIPs, and 256 GB of memory was used. Inferencing was done with Machine Learning for z/OS 2.4 running on Websphere Application Server Liberty 126.96.36.199, using a synthetic credit card fraud detection model (https://github.com/IBM/ai-on-z-fraud-detection). Server-side batching was enabled on Machine Learning for z/OS with a size of 8 inference operations. Results may vary.