MANAGING AI IN THE ENTERPRISE : succeeding with ai projects and mlops to build sustainable ai... organizations

Delivering AI projects and building an AI organization are two big challenges for enterprises. They determine whether companies succeed or fail in establishing AI and integrating AI into their digital transformation. This book addresses both challenges by bringing together organizational and service design concepts, project management, and testing and quality assurance. It covers crucial, often-overlooked topics such as MLOps, IT risk, security and compliance, and AI ethics. In particular, the book shows how to shape AI projects and the capabilities of an AI line organization in an enterprise. It elaborates critical deliverables and milestones, helping you turn your vision into a corporate reality by efficiently managing and setting goals for data scientists, data engineers, and other IT specialists. For those new to AI or AI in an enterprise setting you will find this book a systematic introduction to the field. You will get the necessary know-how to collaborate with and lead AI specialists and guide them to success. Time-pressured readers will benefit from self-contained sections explaining key topics and providing illustrations for fostering discussions in their next team, project, or management meeting. Reading this book helps you to better sell the business benefits from your AI initiatives and build your skills around scoping and delivering AI projects. You will be better able to work through critical aspects such as quality assurance, security, and ethics when building AI solutions in your organization. What You Will Learn Clarify the benefits of your AI initiatives and sell them to senior managers Scope and manage AI projects in your organization Set up quality assurance and testing for AI models and their integration in complex software solutions Shape and manage an AI delivery organization, thereby mastering ML Ops Understand and formulate requirements for the underlying data management infrastructure Handle AI-related IT security, compliance, and risk topics and understand relevant AI ethics aspects Who This Book Is For Experienced IT managers managing data scientists or who want to get involved in managing AI projects, data scientists and other tech professionals who want to progress toward taking on leadership roles in their organization’s AI initiatives and who aim to structure AI projects and AI organizations, any line manager and project manager involved in AI projects or in collaborating with AI teams Table of Contents About the Author About the Technical Reviewer Acknowledgments Introduction Chapter 1: Why Organizations Invest in AI The Role of AI in Data-Driven Companies Calculating the Business Value of AI Use Case: Sales Operations Efficiency How and Why Up-Selling, Cross-Selling, Churn Use Cases Thrive Hurdles and Prerequisites for Success Organizational Impact Insights for Product Strategies Identifying the Business Challenge AI and Analytics vs. Excel Understanding the AI Project Deliverables and Methodology AI-Driven Innovation in Fashion Business Intelligence and AI Summary Chapter 2: Structuring and Delivering AI Projects The Four Layers of Innovation Scoping AI Projects Understanding the Business Goal Understand the Insights Category “Prediction Only” vs. “Prediction and Explanation” The Training Set Challenge Model Update and Usage Frequency Identify the Suitable AI Layer From Scoping Questions to Business Cases Understanding AI Models Statistics-Based Models Neural Networks Advanced Neural Network Topologies Developing AI Models The Jupyter Notebook Phenomenon CRISP-DM for Model Development Improving the Productivity of Data Scientists Integrating AI Models in IT Solutions Summary Chapter 3: Quality Assurance in and for AI AI Model Quality Metrics Performance Metrics for Classification Classification and Scoring Additional Performance Metrics QA Stages in AI Model Engineering Perfect but Worthless Model Metrics The Training, Validation, and Test Data Split Assessing the AI Model with the Training Dataset Assessing the AI Model with the Validation Dataset Assessing the AI Model with the Test Dataset Monitoring AI Models in Production Data Quality Technical Correctness Data Matches Reality? Reputation of Data QA for AI-Driven Solutions Summary Chapter 4: Ethics, Regulations, and Explainability AI Ethics The Three Areas of Ethical Risks Handling Ethical Dilemmas On Ethical AI Models AI Ethics Governance AI and Regulations Data Privacy Laws: The GDPR Example The EU’s “AI Act” Proposal The Federal Trade Commission’s Approach in the US Explainable AI Scenarios for XAI Local Explainability Global Explainability Summary Chapter 5: Building an AI Delivery Organization Shaping an AI Service IT Services Characteristics AI Service Types Characterizing AI Service Types Understanding Service Attributes Designing (for) and Measuring Service Quality Managing AI Project Services The Capabilities Triumvirate for AI Project Services Workload Pattern Budgets and Costs Selling Results: Data Story Telling Managing AI Operations Services The Six AI Capabilities Workload Pattern Understanding and Managing Costs Drivers Model Management Organizing an AI Organization Summary Chapter 6: AI and Data Management Architectures Architecting AI Environments Ingestion Data into AI Environments Storing Training Data Data Lakes vs. Data Warehouses Data Catalogs Model and Code Repositories Executing AI Models AI and Data Management Architectures AI and Classic Data Warehouse Architectures Self-Service Business Intelligence Pantheistic Intelligence New Data Categories Cloud Services and AI Architecture Summary Chapter 7: Securing and Protecting AI Environments The CIA Triangle Security-Related Responsibilities Mapping the Risk Landscape Threat Actors Assets in AI Organizations Confidentiality Threats Integrity Threats Availability Threats From Threats to Risks and Mitigation Securing AI-Related Systems System Hardening Governance Data Compartmentalization and Access Management Advanced Techniques for Sensitive Attributes Probing Detection Cloud-AI Risk Mitigation The ISO 27000 Information Security Standard Summary Chapter 8: Looking Forward Index Delivering AI projects and building an AI organization are two big challenges for enterprises. They determine whether companies succeed or fail in establishing AI and integrating AI into their digital transformation. This book addresses both challenges by bringing together organizational and service design concepts, project management, and testing and quality assurance. It covers crucial, often-overlooked topics such as MLOps, IT risk, security and compliance, and AI ethics. In particular, the book shows how to shape AI projects and the capabilities of an AI line organization in an enterprise. It elaborates critical deliverables and milestones, helping you turn your vision into a corporate reality by efficiently managing and setting goals for data scientists, data engineers, and other IT specialists. For those new to AI or AI in an enterprise setting you will find this book a systematic introduction to the field. You will get the necessary know-how to collaborate with and lead AI specialists and guide them to success. Time-pressured readers will benefit from self-contained sections explaining key topics and providing illustrations for fostering discussions in their next team, project, or management meeting. Reading this book helps you to better sell the business benefits from your AI initiatives and build your skills around scoping and delivering AI projects. You will be better able to work through critical aspects such as quality assurance, security, and ethics when building AI solutions in your organization. -- Provided by publisher