Optimized Inferencing and Integration with AI on IBM zSystems: Introduction, Methodology, and Use Cases

An IBM Redpaper publication

thumbnail 

Published on 17 November 2022, updated 30 November 2022

  1. .EPUB (1.5 MB)
  2. .PDF (3.2 MB)

Apple BooksGoogle Play Books
Share this page:   

ISBN-10: 0738460923
ISBN-13: 9780738460925
IBM Form #: REDP-5661-01


Authors: Makenzie Manna, Erhan Mengusoglu, Artem Minin, Krishna Teja Rekapalli, Thomas Rüter, Pia Velazco and Markus Wolff

    menu icon

    Abstract

    In today’s fast-paced, ever-growing digital world, you face various new and complex business problems. To help resolve these problems, enterprises are embedding artificial intelligence (AI) into their mission-critical business processes and applications to help improve operations, optimize performance, personalize the user experience, and differentiate themselves from the competition.

    Furthermore, the use of AI on the IBM® zSystems platform, where your mission-critical transactions, data, and applications are installed, is a key aspect of modernizing business-critical applications while maintaining strict service-level agreements (SLAs) and security requirements. This colocation of data and AI empowers your enterprise to optimally and easily deploy and infuse AI capabilities into your enterprise workloads with the most recent and relevant data available in real time, which enables a more transparent, accurate, and dependable AI experience.

    This IBM Redpaper publication introduces and explains AI technologies and hardware optimizations, such as IBM zSystems Integrated Accelerator for AI, and demonstrates how to leverage certain capabilities and components to enable solutions in business-critical use cases, such as fraud detection and credit risk scoring on the platform. Real-time inferencing with AI models, a capability that is critical to certain industries and use cases such as fraud detection, now can be implemented with optimized performance thanks to innovations like IBM zSystems Integrated Accelerator for AI embedded in the Telum chip within IBM z16™.

    This publication also describes and demonstrates the implementation and integration of the two end-to-end solutions (fraud detection and credit risk), from developing and training the AI models to deploying the models in an IBM z/OS® V2R5 environment on IBM z16 hardware, and to integrating AI functions into an application, for example an IBM z/OS Customer Information Control System (IBM CICS®) application.

    We describe performance optimization recommendations and considerations when leveraging AI technology on the IBM zSystems platform, including optimizations for micro-batching in IBM Watson® Machine Learning for z/OS (WMLz). The benefits that are derived from the solutions also are described in detail, which includes how the open-source AI framework portability of the IBM zSystems platform enables model development and training to be done anywhere, including on IBM zSystems, and the ability to easily integrate to deploy on IBM zSystems for optimal inferencing. You can uncover insights at the transaction level while taking advantage of the speed, depth, and securability of the platform.

    This publication is intended for technical specialists, site reliability engineers, architects, system programmers, and systems engineers. Technologies that are covered include TensorFlow Serving, WMLz, IBM Cloud Pak® for Data (CP4D), IBM z/OS Container Extensions (zCX), IBM Customer Information Control System (IBM CICS), Open Neural Network Exchange (ONNX), and IBM Deep Learning Compiler (zDLC).

    Table of Contents

    Chapter 1. Foundations of artificial intelligence

    Chapter 2. Methodology and tools

    Chapter 3. Real-time, in-transaction scoring use case scenarios

    Chapter 4. Other use case scenarios

    Chapter 5. Key takeaways

    Appendix A. Installation and configuration pointers

    Appendix B. Additional material