Umfang:
1 Online-Ressource (278 Seiten)
ISBN:
9783030788216
,
9783030788209
Anmerkung:
Intro -- Acknowledgments -- Introduction to Volume III-Data Storage, Data Processing and Data Analysis -- Contents -- Notes on Contributors -- List of Figures -- List of Tables -- Big Data and Special Databases -- Data Lineage -- 1 Introduction and Motivation -- 1.1 Regulatory Requirements -- 1.2 Group-Wide End-to-End Documentation -- 1.3 Benefits of Data Lineage -- 1.3.1 Documentation, Understanding of Data and Data Flows -- 1.3.2 Introduction of New Systems and Software -- 1.3.3 Error Detection and Troubleshooting -- 1.3.4 Data Lineage as a Prerequisite for Data Governance and Data Quality -- 1.3.5 Centralized Maintenance and Master Data Management -- 1.3.6 Information Security -- 1.3.7 Elimination of Redundancies -- 1.3.8 Impact Analysis -- 2 How to Define Data Lineage and Challenges -- 2.1 Horizontal vs. Vertical Data Lineage -- 2.2 Granularity Level of Data Lineage -- 2.2.1 Complex Transformations and Algorithms -- 2.2.2 Black-Box (Closed-Source) Third-Party Applications -- 2.2.3 Data Lineage Covering Business and Regulatory Requirements -- 2.3 Multidimensional Lineage Including Additional Governance -- 3 Approaches to Create a Data Lineage -- 3.1 Data Lineage as a Result of Modeling: Model-Driven Approach -- 3.2 Creating Data Lineage by Reverse Engineering -- 3.3 Hybrid Approach -- 4 Tools Used for Data Lineage -- 4.1 SAP PowerDesigner -- 4.2 ETL Tools -- 4.3 Data Lineage Extraction Tools -- 4.4 Apache Atlas -- 4.5 Graph Databases -- 5 Conclusion -- Literature -- Digitization and MongoDB-The Art of Possible -- 1 Introduction -- 2 Organizational Flexibility and Data Domains -- 3 De-siloing Applications -- 4 The Three Different Paths Leading to the Cloud(s) -- 4.1 Lift and Shift -- 4.2 The Cloud Provider Option -- 4.3 MongoDB Cloud-The Cloud Data Solution -- 5 Summary -- Literature -- Graph Databases -- 1 Introduction
,
1.1 Mathematical Background -- 1.2 Graph Databases in Financial Services -- 2 Technical Implementation -- 2.1 Data Model -- 2.2 Storage -- 2.3 Providers -- 2.4 Visualization of Graph Data -- 2.5 User-Friendly Approach to Graph Databases -- 3 Analysis of Graph Databases -- 3.1 Graph Query Languages -- 4 Business Use Cases -- 4.1 Fraud Detection-Panama Papers -- 4.2 Lufthansa-In-Flight Entertainment System Management -- 4.3 Navigation Systems -- 5 Summary -- Literature -- Data Tiering Options with SAP HANA and Usage in a Hadoop Scenario -- 1 Motivation -- 1.1 Trends in Data Technology -- 1.2 SAP HANA and Hadoop: Best of Both Worlds -- 2 Data Tiering -- 2.1 Overview Data Tiering Options in SAP HANA -- 2.1.1 Hot Data Tiering -- 2.1.2 Warm Data Tiering -- 2.1.3 Cold Data Tiering -- 2.2 Data Tiering with Hadoop and Data Lifecycle Manager (Native HANA) -- 2.2.1 Spark Controller -- 2.2.2 SAP Vora -- 2.2.3 Data Lifecycle Manager and Data Export from SAP HANA to Hadoop -- 3 Conclusion -- Literature -- Streaming -- Kafka: Real-Time Streaming for the Finance Industry -- 1 Introduction -- 1.1 Structure of the Article -- 2 Finance Industry's Common Challenges with Standard Software -- 2.1 Limited Functionality and Negative User Experience -- 2.2 Cost -- 2.3 Inability to Adapt to Changes Quickly -- 2.4 Data Silos -- 3 Kafka Fundamentals-A Quick Tour -- 4 Kafka Use Cases -- 4.1 Accounting Pre-processing -- 4.2 Application and System Integration -- 5 Deployment -- 6 Summary -- Literature -- Architecture Patterns-Batch and Real-Time Capabilities -- 1 Introduction-From Greek Letters to Architecture Patterns -- 2 Lambda Architecture -- 2.1 Batch Layer -- 2.2 Speed Layer -- 2.3 Serving Layer -- 2.4 Benefits of the Lambda Architecture -- 2.5 Limitations of the Lambda Architecture -- 2.6 Summary -- 3 Kappa Architecture -- 3.1 Layers of the Kappa Architecture
,
3.2 Benefits and Limitations of the Kappa Architecture -- 4 Lambda vs. Kappa Architecture -- 5 Other Upcoming Architecture Patterns -- 6 Conclusion and Outlook -- Literature -- Kafka-A Practical Implementation of Intraday Liquidity Risk Management -- 1 Introduction -- 1.1 Initial Situation -- 1.2 General Idea -- 1.3 Structure of the Article -- 2 Practical Implementation -- 2.1 General Architecture -- 2.2 Data Streaming and Preprocessing with Kafka -- 2.3 Machine Learning Method Review -- 2.4 R with Kafka -- 2.5 Demo and Screenshots -- 3 Summary -- Literature -- Data: A View of Meta Aspects -- Data Sustainability-A Thorough Consideration -- 1 Introduction -- 2 Data Security -- 3 Data Compliance -- 4 Societal Conclusion on Data Sustainability -- 5 Data Trash -- 6 Energy Source -- 7 Environmental Conclusion on Data Sustainability -- 8 Summary -- Literature -- Special Data for Insurance Companies -- 1 Introduction -- 2 Wearables in Life and Health -- 2.1 Opportunities -- 2.2 Challenges -- 2.3 Conclusion -- 3 Telematics in Car Insurance -- 3.1 The Different Kinds of Telematics Insurance -- 3.2 Which Way to Go? -- 4 Data Aggregators and Platform-Based Ecosystems -- 5 A Peek into the Future -- Literature -- Data Protection-Putting the Brakes on Digitalization Processes? -- 1 Introduction -- 2 Data Protection -- 3 Instances for Data Protection Regulation -- 3.1 EU-General Data Protection Regulation (GDPR). -- 3.2 USA-California Consumer Privacy Act (CCPA). -- 3.3 Canada-Privacy Act -- 3.4 Japan-Act on the Protection of Personal Information (APPI) -- 3.5 Summary and Brief Comparison -- 4 Impact of Data Protection Regulations on Businesses and Technological Progress -- 4.1 Challenges for Data Processing due to Purpose Restrictions -- 4.1.1 Software Development and Testing -- 4.1.2 Restrictions for Data Trading
,
4.2 Restrictions for Using Artificial Intelligence (AI) and Algorithm-Based Decision-Making -- 4.3 Impacts of the Storage Limitations and the "Right to be Forgotten" -- 5 Summary and Outlook -- Literature -- Distributed Ledger -- Digital Identity Management-For Humans Only? -- 1 Theoretical Basis of Digital Identity Management -- 1.1 Why Is Identification so Important? -- 1.2 How to Identify a Person Beyond Doubt -- 1.3 Verifiable Credentials as an Additional Level of Trust -- 1.4 Self-Sovereign Digital Identity (SSI) -- 2 Technical Implementation of SSI -- 2.1 Decentralized Identifiers -- 2.2 Decentralized Key Management System (DKMS) -- 2.3 DID Auth -- 2.4 Verifiable Credentials -- 3 Applications and Use Cases for Digital Identities -- 3.1 Verifiable Work History Credentials -- 3.2 From Personal to Corporate Identities -- 4 Conclusion -- Literature -- Machine Learning and Deep Learning -- Overview Machine Learning and Deep Learning Frameworks -- 1 Introduction -- 2 Origins -- 2.1 Standard Software Vendors -- 2.2 Universities -- 2.3 Big Techs -- 2.4 Others -- 2.4.1 Open-Source Foundations -- 2.4.2 Hardware Vendors -- 2.4.3 New Software Vendors -- 3 Frameworks -- 3.1 Machine Learning -- 3.1.1 Amazon Machine Learning -- 3.1.2 Ayasdi -- 3.1.3 Apache SystemDS -- 3.1.4 DAAL -- 3.1.5 Dlib -- 3.1.6 ELKI -- 3.1.7 Google Prediction API -- 3.1.8 H2O.ai -- 3.1.9 IBM SPSS Modeler -- 3.1.10 IBM Watson Studio -- 3.1.11 Infer.NET -- 3.1.12 LightGBM -- 3.1.13 LIONsolver -- 3.1.14 Microsoft Azure Machine Learning -- 3.1.15 Microsoft Azure Cognitive Services -- 3.1.16 Mahout -- 3.1.17 MALLET -- 3.1.18 ML.NET -- 3.1.19 mlpack -- 3.1.20 MOA -- 3.1.21 NeuroSolutions -- 3.1.22 Oracle Data Mining -- 3.1.23 Oracle AI Platform -- 3.1.24 PolyAnalyst -- 3.1.25 RCASE -- 3.1.26 SAP Leonardo Machine Learning -- 3.1.27 SAP InfiniteInsight -- 3.1.28 SAS Enterprise Miner
,
3.1.29 scikit-learn -- 3.1.30 Shogun -- 3.1.31 Spark MLlib/SparkML -- 3.1.32 XGBoost -- 3.2 Deep Learning -- 3.2.1 Apache MXNet -- 3.2.2 BigDL -- 3.2.3 Caffe/Caffe2 -- 3.2.4 Chainer -- 3.2.5 CNTK -- 3.2.6 Darknet -- 3.2.7 Deeplearning4j -- 3.2.8 Deep Learning Toolbox (MATLAB) -- 3.2.9 DeepSpeed -- 3.2.10 DyNet -- 3.2.11 fast.ai -- 3.2.12 Flux -- 3.2.13 Gluon -- 3.2.14 MXNet -- 3.2.15 Neural Lab -- 3.2.16 Open AI -- 3.2.17 OpenCV -- 3.2.18 PapplePaddle -- 3.2.19 PlaidML -- 3.2.20 TensorFlow -- 3.2.21 Theano -- 3.2.22 Torch/PyTorch -- 3.2.23 SINGA -- 3.3 Special Frameworks for Natural Language Processing (NLP) -- 3.3.1 Apache cTAKES -- 3.3.2 BERT/mBERT -- 3.3.3 DeepNL -- 3.3.4 ERNIE -- 3.3.5 Gensim -- 3.3.6 Microsoft Icecaps -- 3.3.7 nlpnet -- 3.3.8 OpenNMT -- 3.3.9 SpaCy -- 3.3.10 Stanford CoreNLP -- 3.3.11 Texar-PyTorch -- 3.3.12 Transformers -- 3.4 Integrated Data Handling, Data Mining and Modeling Tools -- 3.4.1 Artelnics -- 3.4.2 Alteryx -- 3.4.3 Dataiku -- 3.4.4 Neural Designer -- 3.4.5 Dplyr / tidyverse -- 3.4.6 Faculty AI -- 3.4.7 KNIME -- 3.4.8 Kedro -- 3.4.9 Orange -- 3.4.10 Palantir Technologies -- 3.4.11 Pandas -- 3.4.12 RapidMiner -- 3.4.13 ROOT (TMVA with ROOT) -- 3.4.14 ThetaRay -- 3.4.15 Weka -- 3.5 Mathematical Software -- 3.5.1 Mathematica -- 3.5.2 MATLAB -- 3.5.3 Sage -- 4 Programming Language -- 4.1 Implementation -- 4.2 Interfaces -- 4.3 Model Description Standards and Universal Interfaces to Frameworks -- 4.3.1 Keras -- 4.3.2 nGraph -- 4.3.3 NNEF -- 4.3.4 ONNX -- 5 Summary -- Literature -- Methods of Machine Learning -- 1 Introduction -- 2 Model validation -- 2.1 Confusion Matrix and Classification Thresholds -- 2.2 ROC Curve and ROC-AUC -- 2.3 Accuracy -- 2.4 Precision and Recall -- 3 Imbalanced Data -- 3.1 Oversampling and Undersampling -- 3.2 Cost-Sensitive Learning -- 3.3 Performance Metrics -- 4 Model Interpretability
,
4.1 Intrinsic Interpretability
Weitere Ausg.:
Erscheint auch als Druck-Ausgabe Liermann, Volker The Digital Journey of Banking and Insurance, Volume III Cham : Springer International Publishing AG,c2021 ISBN 9783030788209
Sprache:
Englisch