Preface

13

What Is the Impact of Machine Learning?

13

What Ethical Aspects Will Be Considered?

14

What Is the Objective of This Book?

16

What Is the Target Audience for This book?

18

1 Introduction to Predictive Intelligence

19

1.1 The Intelligent Enterprise

19

1.2 How Predictive Intelligence Is Evolving at SAP

22

1.3 Connected End-to-End Scenarios

24

1.3.1 Modular Approach

25

1.3.2 Example Scenarios

25

1.4 Analytics of the Future

32

1.4.1 Unified Analytics

33

1.4.2 Business Problems and Business Needs

34

1.4.3 Trends and Technologies

35

1.4.4 User Roles with Analytics

35

1.5 Summary

37

2 The Evolution of Predictive Analytics and Machine Learning at SAP

39

2.1 Predictive Analytics and Machine Learning before SAP S/4HANA

39

2.2 Technologies and Methodologies

40

2.2.1 Automated Analytics

41

2.2.2 Expert Analytics

44

2.3 Best Practices

45

2.4 Summary

48

3 Tools, Technologies, and Services

49

3.1 Machine Learning and Predictive Analytics Approaches

49

3.2 Embedded Machine Learning and Predictive Analytics

51

3.2.1 Overview

51

3.2.2 Embedded Machine Learning with the SAP HANA Automated Predictive Library

53

3.2.3 Embedded Machine Learning with the SAP HANA Predictive Analysis Library

55

3.3 SAP Cloud Platform

57

3.3.1 SAP Data Intelligence

57

3.3.2 Hybrid Machine Learning Models

62

3.4 SAP Analytics Cloud

63

3.4.1 Overview

63

3.4.2 Smart Assist Services

65

3.4.3 Smart Predict Services

67

3.5 SAP Intelligent Robotic Process Automation

70

3.6 SAP Internet of Things

76

3.7 Summary

80

4 Architecture

83

4.1 Introduction

83

4.1.1 Technical Challenges in SAP S/4HANA

83

4.1.2 How to Operationalize Intelligence

84

4.2 Architecture Overview

90

4.2.1 Machine Learning Application Patterns

90

4.2.2 Guiding Principles for Solution Architecture

94

4.2.3 Solution Architecture

95

4.3 Embedded Machine Learning

97

4.4 Side-by-Side Machine Learning

102

4.5 Side-by-Side Predictive Analytics

114

4.6 Summary

118

5 Technical Implementation

119

5.1 Approach Comparison

119

5.2 Implementing Embedded Machine Learning Applications

122

5.2.1 Generated Approach Based on the SAP HANA Automated Predictive Library

123

5.2.2 Coded Approach Based on the SAP HANA Predictive Analysis Library

131

5.3 Implementing Side-by-Side Machine Learning Applications

137

5.3.1 Required Development in SAP Data Intelligence

137

5.3.2 Required Development in ABAP

144

5.4 Implementing Side-by-Side Predictive Analytics Applications

148

5.5 Application Management Processes

155

5.5.1 Lifecycle Management

155

5.5.2 Data Integration

169

5.5.3 Data Protection and Privacy

183

5.5.4 Configuration

194

5.5.5 Extensibility

200

5.5.6 Model Degradation

215

5.5.7 Explanation of Results

221

5.5.8 Workload Management and Performance

229

5.5.9 Legal Auditing

237

5.5.10 Model Validations

244

5.5.11 User Interface Design

252

5.6 Summary

260

6 Business Implementation

261

6.1 Overview of Intelligent Scenarios

261

6.1.1 Creating a Purchase Requisition as an Employee

262

6.1.2 Processing a Purchase Requisition as an Operational Purchaser

263

6.1.3 Monitoring the Spend as a Strategic Purchaser

264

6.1.4 Creating Sales Inquiries as a Sales Manager

264

6.1.5 Recording Financial Transactions as an Accounts Receivable Manager

265

6.2 Configuration Basics

266

6.2.1 SAP Best Practices Explorer

267

6.2.2 SAP Help Portal

271

6.3 Finance

272

6.3.1 SAP Cash Application

273

6.3.2 Accounting and Financial Close

280

6.3.3 Financial Planning and Analysis

285

6.3.4 Governance, Risk, and Compliance

289

6.3.5 Detect Abnormal Liquidity Items

293

6.4 Sourcing and Procurement

295

6.4.1 Contract Consumption

296

6.4.2 Propose Resolution for Invoice Payment Block

297

6.4.3 Supplier Delivery Prediction

299

6.4.4 Proposal of New Catalog Item

300

6.4.5 Proposal of Material Group

301

6.4.6 Proposal of Options for Materials without Purchase Contract

303

6.4.7 Image-Based Buying

305

6.4.8 Intelligent Approval Workflow

306

6.4.9 Blockchain-Verified RFQ Processing

307

6.5 Inventory and Supply Chain

308

6.5.1 Stock in Transit

309

6.5.2 Demand-Driven Replenishment

311

6.5.3 Defect Code Proposal with Text Recognition

313

6.5.4 Early Detection of Slow and Nonmoving Stock

315

6.6 Sales

317

6.6.1 Predict Conversion of Sales Quotations to Sales Orders

318

6.6.2 Predict Sales Forecasts

319

6.6.3 Predict Delivery Delay

322

6.7 Research and Development/Engineering

323

6.7.1 Project Cost Forecasting

324

6.7.2 Digital Content Processing

325

6.8 Industries

327

6.8.1 Professional Services

327

6.8.2 Component Manufacturing

336

6.8.3 Retail

342

6.8.4 Utilities

352

6.8.5 Consumer Products

357

6.8.6 Insurance

360

6.8.7 Telecommunications

364

6.8.8 Banking

368

6.8.9 High-Tech

370

6.8.10 Sports and Entertainment

372

6.8.11 Public Services

373

6.9 Summary

374

7 Services on SAP Cloud Platform

375

7.1 Key Trends and Capabilities

375

7.2 SAP Data Intelligence

382

7.3 Machine Learning

383

7.4 Internet of Things

386

7.5 Blockchain

387

7.6 Summary

388

8 The Road Ahead and Further Learning

389

8.1 Upcoming Features and Functionality

389

8.1.1 Embedded Predictive Models

389

8.1.2 Machine Learning Models on SAP Cloud Platform

390

8.1.3 SAP Analytics Cloud

391

8.1.4 Extensions of Existing Approaches

392

8.2 Blogs for Continuous Information

392

8.3 Summary

393