Applying Data Science: How to Create Value with Artificial Intelligence
Saved in:
| Main Author: | |
|---|---|
| Format: | Electronic eBook |
| Language: | English |
| Published: |
Cham
Springer International Publishing AG
2020
|
| Subjects: | |
| Item Description: | Description based on publisher supplied metadata and other sources |
| Physical Description: | 1 Online-Ressource (511 Seiten) |
| ISBN: | 9783030363758 |
Staff View
MARC
| LEADER | 00000nmm a2200000zc 4500 | ||
|---|---|---|---|
| 001 | BV048224143 | ||
| 003 | DE-604 | ||
| 005 | 00000000000000.0 | ||
| 007 | cr|uuu---uuuuu | ||
| 008 | 220516s2020 |||| o||u| ||||||eng d | ||
| 020 | |a 9783030363758 |9 978-3-030-36375-8 | ||
| 035 | |a (ZDB-30-PQE)EBC6348885 | ||
| 035 | |a (ZDB-30-PAD)EBC6348885 | ||
| 035 | |a (ZDB-89-EBL)EBL6348885 | ||
| 035 | |a (OCoLC)1202483782 | ||
| 035 | |a (DE-599)BVBBV048224143 | ||
| 040 | |a DE-604 |b ger |e rda | ||
| 041 | 0 | |a eng | |
| 082 | 0 | |a 658.0563 | |
| 084 | |a ST 300 |0 (DE-625)143650: |2 rvk | ||
| 100 | 1 | |a Kordon, Arthur K. |e Verfasser |4 aut | |
| 245 | 1 | 0 | |a Applying Data Science |b How to Create Value with Artificial Intelligence |
| 264 | 1 | |a Cham |b Springer International Publishing AG |c 2020 | |
| 264 | 4 | |c ©2020 | |
| 300 | |a 1 Online-Ressource (511 Seiten) | ||
| 336 | |b txt |2 rdacontent | ||
| 337 | |b c |2 rdamedia | ||
| 338 | |b cr |2 rdacarrier | ||
| 500 | |a Description based on publisher supplied metadata and other sources | ||
| 505 | 8 | |a Intro -- Preface -- Motivation -- Purpose of the Book -- Who Is This Book for? -- How This Book Is Structured -- What This Book Is NOT About -- Features of the Book -- Acknowledgments -- Contents -- Part I: From Business Problems to Data Science -- Chapter 1: Data Science Based on Artificial Intelligence -- 1.1 Big Data, Big Mess, Big Opportunity -- 1.1.1 From Hype to Competitive Advantage -- 1.1.2 Key Buzzwords Explained -- 1.1.3 Why Now? -- 1.2 What Is AI-Based Data Science? -- 1.2.1 Definition of AI-Based Data Science -- 1.2.2 Features of AI-Based Data Science -- 1.3 Competitive Advantages of AI-Based Data Science -- 1.3.1 Creating ''Objective Intelligence'' -- 1.3.2 Dealing with Uncertainty -- 1.3.3 Dealing with Complexity -- 1.3.4 Generating Novelty -- 1.3.5 Low-Cost Modeling and Optimization -- 1.4 Key Challenges in Applying AI-Based Data Science -- 1.4.1 Technical Issues in Applying AI-Based Data Science -- 1.4.2 Nontechnical Issues in Applying AI-Based Data Science -- 1.5 Common Mistakes -- 1.5.1 Believing the Hype -- 1.5.2 Neglecting to Estimate the Demand for AI-Based Data Science -- 1.5.3 Mass-Scale Introduction of AI-Based Data Science in a Business without Required Skillset Availability -- 1.5.4 Introducing Data Science Bureaucracy -- 1.6 Suggested Reading -- 1.7 Questions -- Chapter 2: Business Problems Dependent on Data -- 2.1 The Leading Role of Business Problems -- 2.1.1 ''Data Is the New Oil'' Hype -- 2.1.2 Problems-First Approach -- 2.2 Typical Business Problems Related to AI-Based Data Science -- 2.2.1 Typical Problems in Manufacturing -- 2.2.2 Typical Problems in Business -- 2.3 How to Find Data-Driven Business Problems -- 2.3.1 Understand Business Needs -- 2.3.2 Match Business Needs with Known Artificial Intelligence-Based Use Cases -- 2.4 The Slippery Terrain of Problem Definition -- 2.4.1 Structure of Problem Definition | |
| 505 | 8 | |a 2.4.2 Example of Problem Definition -- 2.5 Value Creation Hypothesis -- 2.5.1 Sources of Value Creation -- 2.5.2 Metrics for Value Creation -- 2.6 Common Mistakes -- 2.6.1 Jumping to Solutions without Defining Business Problems -- 2.6.2 Neglecting the Importance of a Detailed Realistic Problem Definition -- 2.6.3 Ignoring Definition of Value Creation Metrics for the Problem -- 2.6.4 Believing in a Data First, Problems Second Approach -- 2.7 Suggested Reading -- 2.8 Questions -- Chapter 3: Artificial Intelligence-Based Data Science Solutions -- 3.1 Typical Solutions Related to Data Science -- 3.1.1 Prediction -- 3.1.2 Forecasting -- 3.1.3 Classification -- 3.1.4 Clustering -- 3.1.5 Optimization -- 3.1.6 Association -- 3.2 Advanced AI Solutions Related to Data Science -- 3.2.1 Natural Language Processing -- 3.2.2 Video/Image Processing -- 3.2.3 Sentiment Analysis -- 3.2.4 Artificial General Intelligence -- 3.3 Key AI Methods in a Nutshell -- 3.3.1 Neural Networks in a Nutshell -- 3.3.2 Deep Learning Networks in a Nutshell -- 3.3.3 Support Vector Machines in a Nutshell -- 3.3.4 Decision Trees in a Nutshell -- 3.3.5 Evolutionary Computation in a utshell -- 3.3.6 Swarm Intelligence in a Nutshell -- 3.3.7 Intelligent Agents in a Nutshell -- 3.4 Common Mistakes -- 3.4.1 Obsession with One Method -- 3.4.2 Focusing on Fashionable Methods -- 3.4.3 Lack of Knowledge about Broad Options for AI-Based Approaches -- 3.4.4 Lack of Knowledge about Cost of Implementation of Methods -- 3.5 Suggested Reading -- 3.6 Questions -- Chapter 4: Integrate and Conquer -- 4.1 The Integrate and Conquer Strategy in Applied Data Science -- 4.1.1 The Nasty Reality of Real-World Applications -- 4.1.2 Why Integration of Methods Is Critical for Real-World Applications -- 4.2 Integration Opportunities -- 4.2.1 Integration Between AI-Based Methods | |
| 505 | 8 | |a 4.2.2 Integration with First-Principles Models -- 4.2.3 Integration with Statistical Models -- 4.2.4 Integration by Ensembles of Models -- 4.3 How to Select the Best Solutions for the Business Problem -- 4.3.1 Capabilities of Methods -- 4.3.2 Applicability of Methods -- 4.3.3 One Method Is Not Enough -- 4.4 Common Mistakes -- 4.4.1 Ignoring Integration of Methods -- 4.4.2 Lack of Knowledge of Strengths and Weaknesses of Methods -- 4.4.3 Lack of Knowledge about Selecting the Most Appropriate Methods for the Business Problem -- 4.5 Suggested Reading -- 4.6 Questions -- Chapter 5: The Lost-in-Translation Trap -- 5.1 Translation from Business Problems to Data Science Solutions -- 5.1.1 Select Best Experts in Problem Domain -- 5.1.2 Generic Problem Questionnaire Template -- 5.1.3 Problem Description by Domain Experts -- 5.1.4 Problem Understanding by Data Scientists -- 5.1.5 Create a Problem-Related Glossary -- 5.2 Translation from Data Science Solutions to Business Problems -- 5.2.1 Explain Data Science Work Process -- 5.2.2 Communicate Potential Data Science Solutions -- 5.2.3 Demonstrate Similar Data Science Use Cases -- 5.2.4 Explain Key Principles Related to Potential Data Science Solutions -- 5.2.5 Create a Solution-Related Glossary -- 5.3 Typical Lost-in-Translation Cases -- 5.3.1 Inexperienced Data Scientists -- 5.3.2 Resistance from Experts -- 5.3.3 Improper Problem Definition -- 5.3.4 Management Intervention -- 5.4 How to Avoid the-Lost-in-Translation Trap -- 5.4.1 Translators -- 5.4.2 Examples of Translators for AI-Methods -- 5.5 Common Mistakes -- 5.5.1 Ignoring the Dialog Between Domain Experts and Data Scientists -- 5.5.2 Ignoring the People Factor -- 5.5.3 Ignoring Team Building -- 5.6 Suggested Reading -- 5.7 Questions -- Part II: The AI-Based Data Science Toolbox -- Chapter 6: The AI-Based Data Science Workflow -- 6.1 Overview of Workflow | |
| 505 | 8 | |a 6.1.1 Why we Need an Effective AI-Based Data Science Workflow -- 6.1.2 Why Is the Classical Scientific Process Not Enough? -- 6.1.3 Comparison with CRISP-DM -- 6.1.4 AI-Based Data Science Workflow Sequence -- 6.2 Key Steps of AI-Based Data Science Workflow -- 6.2.1 Problem Definition -- 6.2.2 Project Organization -- 6.2.3 Problem Knowledge Acquisition -- 6.2.4 Data Preparation -- 6.2.5 Data Analysis -- 6.2.6 Model Development -- 6.2.7 Model Deployment -- 6.2.8 Model Maintenance -- 6.2.9 Automation of AI-Based Data Science Workflow -- 6.3 Project Organization -- 6.3.1 Organizing Project Teams -- 6.3.2 Resources Allocation -- 6.3.3 Project Scheduling -- 6.3.4 Project Funding -- 6.4 Common Mistakes -- 6.4.1 Ignoring a Detailed Workflow -- 6.4.2 Ignoring some Steps in the Workflow -- 6.4.3 Insufficient Efforts on Cost Estimates -- 6.4.4 Not Documenting the Deliverables -- 6.5 Suggested Reading -- 6.6 Questions -- Chapter 7: Problem Knowledge Acquisition -- 7.1 Importance of Problem Knowledge -- 7.1.1 Problem Knowledge in Problem Definition -- 7.1.2 Problem Knowledge in Data Preparation -- 7.1.3 Problem Knowledge in Data Analysis -- 7.1.4 Problem Knowledge in Model Development -- 7.1.5 Problem Knowledge in Model Deployment -- 7.2 Sources of Problem Knowledge -- 7.2.1 Subject Matter Experts -- 7.2.2 Problem-Related Documents -- 7.2.3 Publicly Available References -- 7.3 Problem Knowledge Acquisition Methods -- 7.3.1 Mind Mapping -- 7.3.2 Brainstorming Sessions -- 7.3.3 External Knowledge Acquisition -- 7.3.4 Knowledge Acquisition Skills -- 7.4 Problem Knowledge Integration -- 7.4.1 Define Recommended Assumptions -- 7.4.2 Define Normal/Abnormal Operating Conditions -- 7.4.3 Suggest Selection of Initial Variables -- 7.4.4 Define Qualitative Performance Metric -- 7.5 Definition of a Problem Solution Strategy -- 7.5.1 Define Solution Hypotheses | |
| 505 | 8 | |a 7.5.2 Define a List of Potential Solutions -- 7.5.3 Define Issues and Limitations of Suggested Solutions -- 7.5.4 Define Needed Infrastructure -- 7.6 Common Mistakes -- 7.6.1 Focusing on Data and Ignoring Problem Knowledge -- 7.6.2 SMEs Are Not Involved -- 7.6.3 Not Validating SMEs Knowledge -- 7.6.4 Reinventing the Wheel -- 7.7 Suggested Reading -- 7.8 Questions -- Chapter 8: Data Preparation -- 8.1 Data Collection -- 8.1.1 Data Sources -- 8.2 Visual Data Exploration -- 8.2.1 Strange Data Patterns -- 8.2.2 Data Distributions -- 8.2.3 Univariate Plots -- 8.2.4 Bivariate Plots -- 8.2.5 Multivariate Plots -- 8.3 Data Preprocessing -- 8.3.1 Handling Missing Data -- 8.3.2 Handling Outliers -- 8.3.3 Data Transformation -- 8.3.4 Data Balance -- 8.3.5 Data Quality Assessment -- 8.4 Common Mistakes -- 8.4.1 GIGO 2.0 -- 8.4.2 Problem Solving with Insufficient Data -- 8.4.3 Problem Solving with Low-Quality Data -- 8.4.4 Low-Quality Data Preparation -- 8.5 Suggested Reading -- 8.6 Questions -- Chapter 9: Data Analysis -- 9.1 Translation of Data into Insight -- 9.1.1 Problem Knowledge Gain from Data Analysis -- 9.1.2 Insight from Multivariate View -- 9.1.3 Insight from Understanding Key Drivers -- 9.1.4 Insight from Discovered Features and Patterns -- 9.1.5 Insight from Data Analysis as the Final Problem Solution -- 9.1.6 Insight for Final Data Preparation for Modeling -- 9.2 Multivariate Data Analysis -- 9.2.1 Principal Component Analysis -- 9.2.2 Multivariate Patterns -- 9.3 Variable Selection -- 9.3.1 Variable Reduction -- 9.3.2 Handling Multicollinearity -- 9.3.3 Linear Variable Selection -- 9.3.4 Nonlinear Variable Selection -- 9.4 Feature Extraction -- 9.4.1 Feature Engineering -- 9.4.2 Automatically Generated Features -- 9.5 Data Visualization -- 9.5.1 Parallel Coordinates Plot -- 9.5.2 Chord Diagram -- 9.5.3 Contour Plot | |
| 505 | 8 | |a 9.6 Data-Analysis-Driven Storytelling | |
| 650 | 4 | |a Artificial intelligence | |
| 650 | 4 | |a Business-Data processing | |
| 650 | 4 | |a Big data | |
| 650 | 0 | 7 | |a Big Data |0 (DE-588)4802620-7 |2 gnd |9 rswk-swf |
| 650 | 0 | 7 | |a Künstliche Intelligenz |0 (DE-588)4033447-8 |2 gnd |9 rswk-swf |
| 689 | 0 | 0 | |a Künstliche Intelligenz |0 (DE-588)4033447-8 |D s |
| 689 | 0 | 1 | |a Big Data |0 (DE-588)4802620-7 |D s |
| 689 | 0 | |5 DE-604 | |
| 776 | 0 | 8 | |i Erscheint auch als |n Druck-Ausgabe |a Kordon, Arthur K. |t Applying Data Science |d Cham : Springer International Publishing AG,c2020 |z 9783030363741 |
| 912 | |a ZDB-30-PQE | ||
| 999 | |a oai:aleph.bib-bvb.de:BVB01-033604876 | ||
Record in the Search Index
| _version_ | 1804184006121488384 |
|---|---|
| adam_txt | |
| any_adam_object | |
| any_adam_object_boolean | |
| author | Kordon, Arthur K. |
| author_facet | Kordon, Arthur K. |
| author_role | aut |
| author_sort | Kordon, Arthur K. |
| author_variant | a k k ak akk |
| building | Verbundindex |
| bvnumber | BV048224143 |
| classification_rvk | ST 300 |
| collection | ZDB-30-PQE |
| contents | Intro -- Preface -- Motivation -- Purpose of the Book -- Who Is This Book for? -- How This Book Is Structured -- What This Book Is NOT About -- Features of the Book -- Acknowledgments -- Contents -- Part I: From Business Problems to Data Science -- Chapter 1: Data Science Based on Artificial Intelligence -- 1.1 Big Data, Big Mess, Big Opportunity -- 1.1.1 From Hype to Competitive Advantage -- 1.1.2 Key Buzzwords Explained -- 1.1.3 Why Now? -- 1.2 What Is AI-Based Data Science? -- 1.2.1 Definition of AI-Based Data Science -- 1.2.2 Features of AI-Based Data Science -- 1.3 Competitive Advantages of AI-Based Data Science -- 1.3.1 Creating ''Objective Intelligence'' -- 1.3.2 Dealing with Uncertainty -- 1.3.3 Dealing with Complexity -- 1.3.4 Generating Novelty -- 1.3.5 Low-Cost Modeling and Optimization -- 1.4 Key Challenges in Applying AI-Based Data Science -- 1.4.1 Technical Issues in Applying AI-Based Data Science -- 1.4.2 Nontechnical Issues in Applying AI-Based Data Science -- 1.5 Common Mistakes -- 1.5.1 Believing the Hype -- 1.5.2 Neglecting to Estimate the Demand for AI-Based Data Science -- 1.5.3 Mass-Scale Introduction of AI-Based Data Science in a Business without Required Skillset Availability -- 1.5.4 Introducing Data Science Bureaucracy -- 1.6 Suggested Reading -- 1.7 Questions -- Chapter 2: Business Problems Dependent on Data -- 2.1 The Leading Role of Business Problems -- 2.1.1 ''Data Is the New Oil'' Hype -- 2.1.2 Problems-First Approach -- 2.2 Typical Business Problems Related to AI-Based Data Science -- 2.2.1 Typical Problems in Manufacturing -- 2.2.2 Typical Problems in Business -- 2.3 How to Find Data-Driven Business Problems -- 2.3.1 Understand Business Needs -- 2.3.2 Match Business Needs with Known Artificial Intelligence-Based Use Cases -- 2.4 The Slippery Terrain of Problem Definition -- 2.4.1 Structure of Problem Definition 2.4.2 Example of Problem Definition -- 2.5 Value Creation Hypothesis -- 2.5.1 Sources of Value Creation -- 2.5.2 Metrics for Value Creation -- 2.6 Common Mistakes -- 2.6.1 Jumping to Solutions without Defining Business Problems -- 2.6.2 Neglecting the Importance of a Detailed Realistic Problem Definition -- 2.6.3 Ignoring Definition of Value Creation Metrics for the Problem -- 2.6.4 Believing in a Data First, Problems Second Approach -- 2.7 Suggested Reading -- 2.8 Questions -- Chapter 3: Artificial Intelligence-Based Data Science Solutions -- 3.1 Typical Solutions Related to Data Science -- 3.1.1 Prediction -- 3.1.2 Forecasting -- 3.1.3 Classification -- 3.1.4 Clustering -- 3.1.5 Optimization -- 3.1.6 Association -- 3.2 Advanced AI Solutions Related to Data Science -- 3.2.1 Natural Language Processing -- 3.2.2 Video/Image Processing -- 3.2.3 Sentiment Analysis -- 3.2.4 Artificial General Intelligence -- 3.3 Key AI Methods in a Nutshell -- 3.3.1 Neural Networks in a Nutshell -- 3.3.2 Deep Learning Networks in a Nutshell -- 3.3.3 Support Vector Machines in a Nutshell -- 3.3.4 Decision Trees in a Nutshell -- 3.3.5 Evolutionary Computation in a utshell -- 3.3.6 Swarm Intelligence in a Nutshell -- 3.3.7 Intelligent Agents in a Nutshell -- 3.4 Common Mistakes -- 3.4.1 Obsession with One Method -- 3.4.2 Focusing on Fashionable Methods -- 3.4.3 Lack of Knowledge about Broad Options for AI-Based Approaches -- 3.4.4 Lack of Knowledge about Cost of Implementation of Methods -- 3.5 Suggested Reading -- 3.6 Questions -- Chapter 4: Integrate and Conquer -- 4.1 The Integrate and Conquer Strategy in Applied Data Science -- 4.1.1 The Nasty Reality of Real-World Applications -- 4.1.2 Why Integration of Methods Is Critical for Real-World Applications -- 4.2 Integration Opportunities -- 4.2.1 Integration Between AI-Based Methods 4.2.2 Integration with First-Principles Models -- 4.2.3 Integration with Statistical Models -- 4.2.4 Integration by Ensembles of Models -- 4.3 How to Select the Best Solutions for the Business Problem -- 4.3.1 Capabilities of Methods -- 4.3.2 Applicability of Methods -- 4.3.3 One Method Is Not Enough -- 4.4 Common Mistakes -- 4.4.1 Ignoring Integration of Methods -- 4.4.2 Lack of Knowledge of Strengths and Weaknesses of Methods -- 4.4.3 Lack of Knowledge about Selecting the Most Appropriate Methods for the Business Problem -- 4.5 Suggested Reading -- 4.6 Questions -- Chapter 5: The Lost-in-Translation Trap -- 5.1 Translation from Business Problems to Data Science Solutions -- 5.1.1 Select Best Experts in Problem Domain -- 5.1.2 Generic Problem Questionnaire Template -- 5.1.3 Problem Description by Domain Experts -- 5.1.4 Problem Understanding by Data Scientists -- 5.1.5 Create a Problem-Related Glossary -- 5.2 Translation from Data Science Solutions to Business Problems -- 5.2.1 Explain Data Science Work Process -- 5.2.2 Communicate Potential Data Science Solutions -- 5.2.3 Demonstrate Similar Data Science Use Cases -- 5.2.4 Explain Key Principles Related to Potential Data Science Solutions -- 5.2.5 Create a Solution-Related Glossary -- 5.3 Typical Lost-in-Translation Cases -- 5.3.1 Inexperienced Data Scientists -- 5.3.2 Resistance from Experts -- 5.3.3 Improper Problem Definition -- 5.3.4 Management Intervention -- 5.4 How to Avoid the-Lost-in-Translation Trap -- 5.4.1 Translators -- 5.4.2 Examples of Translators for AI-Methods -- 5.5 Common Mistakes -- 5.5.1 Ignoring the Dialog Between Domain Experts and Data Scientists -- 5.5.2 Ignoring the People Factor -- 5.5.3 Ignoring Team Building -- 5.6 Suggested Reading -- 5.7 Questions -- Part II: The AI-Based Data Science Toolbox -- Chapter 6: The AI-Based Data Science Workflow -- 6.1 Overview of Workflow 6.1.1 Why we Need an Effective AI-Based Data Science Workflow -- 6.1.2 Why Is the Classical Scientific Process Not Enough? -- 6.1.3 Comparison with CRISP-DM -- 6.1.4 AI-Based Data Science Workflow Sequence -- 6.2 Key Steps of AI-Based Data Science Workflow -- 6.2.1 Problem Definition -- 6.2.2 Project Organization -- 6.2.3 Problem Knowledge Acquisition -- 6.2.4 Data Preparation -- 6.2.5 Data Analysis -- 6.2.6 Model Development -- 6.2.7 Model Deployment -- 6.2.8 Model Maintenance -- 6.2.9 Automation of AI-Based Data Science Workflow -- 6.3 Project Organization -- 6.3.1 Organizing Project Teams -- 6.3.2 Resources Allocation -- 6.3.3 Project Scheduling -- 6.3.4 Project Funding -- 6.4 Common Mistakes -- 6.4.1 Ignoring a Detailed Workflow -- 6.4.2 Ignoring some Steps in the Workflow -- 6.4.3 Insufficient Efforts on Cost Estimates -- 6.4.4 Not Documenting the Deliverables -- 6.5 Suggested Reading -- 6.6 Questions -- Chapter 7: Problem Knowledge Acquisition -- 7.1 Importance of Problem Knowledge -- 7.1.1 Problem Knowledge in Problem Definition -- 7.1.2 Problem Knowledge in Data Preparation -- 7.1.3 Problem Knowledge in Data Analysis -- 7.1.4 Problem Knowledge in Model Development -- 7.1.5 Problem Knowledge in Model Deployment -- 7.2 Sources of Problem Knowledge -- 7.2.1 Subject Matter Experts -- 7.2.2 Problem-Related Documents -- 7.2.3 Publicly Available References -- 7.3 Problem Knowledge Acquisition Methods -- 7.3.1 Mind Mapping -- 7.3.2 Brainstorming Sessions -- 7.3.3 External Knowledge Acquisition -- 7.3.4 Knowledge Acquisition Skills -- 7.4 Problem Knowledge Integration -- 7.4.1 Define Recommended Assumptions -- 7.4.2 Define Normal/Abnormal Operating Conditions -- 7.4.3 Suggest Selection of Initial Variables -- 7.4.4 Define Qualitative Performance Metric -- 7.5 Definition of a Problem Solution Strategy -- 7.5.1 Define Solution Hypotheses 7.5.2 Define a List of Potential Solutions -- 7.5.3 Define Issues and Limitations of Suggested Solutions -- 7.5.4 Define Needed Infrastructure -- 7.6 Common Mistakes -- 7.6.1 Focusing on Data and Ignoring Problem Knowledge -- 7.6.2 SMEs Are Not Involved -- 7.6.3 Not Validating SMEs Knowledge -- 7.6.4 Reinventing the Wheel -- 7.7 Suggested Reading -- 7.8 Questions -- Chapter 8: Data Preparation -- 8.1 Data Collection -- 8.1.1 Data Sources -- 8.2 Visual Data Exploration -- 8.2.1 Strange Data Patterns -- 8.2.2 Data Distributions -- 8.2.3 Univariate Plots -- 8.2.4 Bivariate Plots -- 8.2.5 Multivariate Plots -- 8.3 Data Preprocessing -- 8.3.1 Handling Missing Data -- 8.3.2 Handling Outliers -- 8.3.3 Data Transformation -- 8.3.4 Data Balance -- 8.3.5 Data Quality Assessment -- 8.4 Common Mistakes -- 8.4.1 GIGO 2.0 -- 8.4.2 Problem Solving with Insufficient Data -- 8.4.3 Problem Solving with Low-Quality Data -- 8.4.4 Low-Quality Data Preparation -- 8.5 Suggested Reading -- 8.6 Questions -- Chapter 9: Data Analysis -- 9.1 Translation of Data into Insight -- 9.1.1 Problem Knowledge Gain from Data Analysis -- 9.1.2 Insight from Multivariate View -- 9.1.3 Insight from Understanding Key Drivers -- 9.1.4 Insight from Discovered Features and Patterns -- 9.1.5 Insight from Data Analysis as the Final Problem Solution -- 9.1.6 Insight for Final Data Preparation for Modeling -- 9.2 Multivariate Data Analysis -- 9.2.1 Principal Component Analysis -- 9.2.2 Multivariate Patterns -- 9.3 Variable Selection -- 9.3.1 Variable Reduction -- 9.3.2 Handling Multicollinearity -- 9.3.3 Linear Variable Selection -- 9.3.4 Nonlinear Variable Selection -- 9.4 Feature Extraction -- 9.4.1 Feature Engineering -- 9.4.2 Automatically Generated Features -- 9.5 Data Visualization -- 9.5.1 Parallel Coordinates Plot -- 9.5.2 Chord Diagram -- 9.5.3 Contour Plot 9.6 Data-Analysis-Driven Storytelling |
| ctrlnum | (ZDB-30-PQE)EBC6348885 (ZDB-30-PAD)EBC6348885 (ZDB-89-EBL)EBL6348885 (OCoLC)1202483782 (DE-599)BVBBV048224143 |
| dewey-full | 658.0563 |
| dewey-hundreds | 600 - Technology (Applied sciences) |
| dewey-ones | 658 - General management |
| dewey-raw | 658.0563 |
| dewey-search | 658.0563 |
| dewey-sort | 3658.0563 |
| dewey-tens | 650 - Management and auxiliary services |
| discipline | Informatik Wirtschaftswissenschaften |
| discipline_str_mv | Informatik Wirtschaftswissenschaften |
| format | Electronic eBook |
| fullrecord | <?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>11048nmm a2200517zc 4500</leader><controlfield tag="001">BV048224143</controlfield><controlfield tag="003">DE-604</controlfield><controlfield tag="005">00000000000000.0</controlfield><controlfield tag="007">cr|uuu---uuuuu</controlfield><controlfield tag="008">220516s2020 |||| o||u| ||||||eng d</controlfield><datafield tag="020" ind1=" " ind2=" "><subfield code="a">9783030363758</subfield><subfield code="9">978-3-030-36375-8</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ZDB-30-PQE)EBC6348885</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ZDB-30-PAD)EBC6348885</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ZDB-89-EBL)EBL6348885</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(OCoLC)1202483782</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)BVBBV048224143</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-604</subfield><subfield code="b">ger</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1="0" ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2=" "><subfield code="a">658.0563</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">ST 300</subfield><subfield code="0">(DE-625)143650:</subfield><subfield code="2">rvk</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Kordon, Arthur K.</subfield><subfield code="e">Verfasser</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Applying Data Science</subfield><subfield code="b">How to Create Value with Artificial Intelligence</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="a">Cham</subfield><subfield code="b">Springer International Publishing AG</subfield><subfield code="c">2020</subfield></datafield><datafield tag="264" ind1=" " ind2="4"><subfield code="c">©2020</subfield></datafield><datafield tag="300" ind1=" " ind2=" "><subfield code="a">1 Online-Ressource (511 Seiten)</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">Description based on publisher supplied metadata and other sources</subfield></datafield><datafield tag="505" ind1="8" ind2=" "><subfield code="a">Intro -- Preface -- Motivation -- Purpose of the Book -- Who Is This Book for? -- How This Book Is Structured -- What This Book Is NOT About -- Features of the Book -- Acknowledgments -- Contents -- Part I: From Business Problems to Data Science -- Chapter 1: Data Science Based on Artificial Intelligence -- 1.1 Big Data, Big Mess, Big Opportunity -- 1.1.1 From Hype to Competitive Advantage -- 1.1.2 Key Buzzwords Explained -- 1.1.3 Why Now? -- 1.2 What Is AI-Based Data Science? -- 1.2.1 Definition of AI-Based Data Science -- 1.2.2 Features of AI-Based Data Science -- 1.3 Competitive Advantages of AI-Based Data Science -- 1.3.1 Creating ''Objective Intelligence'' -- 1.3.2 Dealing with Uncertainty -- 1.3.3 Dealing with Complexity -- 1.3.4 Generating Novelty -- 1.3.5 Low-Cost Modeling and Optimization -- 1.4 Key Challenges in Applying AI-Based Data Science -- 1.4.1 Technical Issues in Applying AI-Based Data Science -- 1.4.2 Nontechnical Issues in Applying AI-Based Data Science -- 1.5 Common Mistakes -- 1.5.1 Believing the Hype -- 1.5.2 Neglecting to Estimate the Demand for AI-Based Data Science -- 1.5.3 Mass-Scale Introduction of AI-Based Data Science in a Business without Required Skillset Availability -- 1.5.4 Introducing Data Science Bureaucracy -- 1.6 Suggested Reading -- 1.7 Questions -- Chapter 2: Business Problems Dependent on Data -- 2.1 The Leading Role of Business Problems -- 2.1.1 ''Data Is the New Oil'' Hype -- 2.1.2 Problems-First Approach -- 2.2 Typical Business Problems Related to AI-Based Data Science -- 2.2.1 Typical Problems in Manufacturing -- 2.2.2 Typical Problems in Business -- 2.3 How to Find Data-Driven Business Problems -- 2.3.1 Understand Business Needs -- 2.3.2 Match Business Needs with Known Artificial Intelligence-Based Use Cases -- 2.4 The Slippery Terrain of Problem Definition -- 2.4.1 Structure of Problem Definition</subfield></datafield><datafield tag="505" ind1="8" ind2=" "><subfield code="a">2.4.2 Example of Problem Definition -- 2.5 Value Creation Hypothesis -- 2.5.1 Sources of Value Creation -- 2.5.2 Metrics for Value Creation -- 2.6 Common Mistakes -- 2.6.1 Jumping to Solutions without Defining Business Problems -- 2.6.2 Neglecting the Importance of a Detailed Realistic Problem Definition -- 2.6.3 Ignoring Definition of Value Creation Metrics for the Problem -- 2.6.4 Believing in a Data First, Problems Second Approach -- 2.7 Suggested Reading -- 2.8 Questions -- Chapter 3: Artificial Intelligence-Based Data Science Solutions -- 3.1 Typical Solutions Related to Data Science -- 3.1.1 Prediction -- 3.1.2 Forecasting -- 3.1.3 Classification -- 3.1.4 Clustering -- 3.1.5 Optimization -- 3.1.6 Association -- 3.2 Advanced AI Solutions Related to Data Science -- 3.2.1 Natural Language Processing -- 3.2.2 Video/Image Processing -- 3.2.3 Sentiment Analysis -- 3.2.4 Artificial General Intelligence -- 3.3 Key AI Methods in a Nutshell -- 3.3.1 Neural Networks in a Nutshell -- 3.3.2 Deep Learning Networks in a Nutshell -- 3.3.3 Support Vector Machines in a Nutshell -- 3.3.4 Decision Trees in a Nutshell -- 3.3.5 Evolutionary Computation in a utshell -- 3.3.6 Swarm Intelligence in a Nutshell -- 3.3.7 Intelligent Agents in a Nutshell -- 3.4 Common Mistakes -- 3.4.1 Obsession with One Method -- 3.4.2 Focusing on Fashionable Methods -- 3.4.3 Lack of Knowledge about Broad Options for AI-Based Approaches -- 3.4.4 Lack of Knowledge about Cost of Implementation of Methods -- 3.5 Suggested Reading -- 3.6 Questions -- Chapter 4: Integrate and Conquer -- 4.1 The Integrate and Conquer Strategy in Applied Data Science -- 4.1.1 The Nasty Reality of Real-World Applications -- 4.1.2 Why Integration of Methods Is Critical for Real-World Applications -- 4.2 Integration Opportunities -- 4.2.1 Integration Between AI-Based Methods</subfield></datafield><datafield tag="505" ind1="8" ind2=" "><subfield code="a">4.2.2 Integration with First-Principles Models -- 4.2.3 Integration with Statistical Models -- 4.2.4 Integration by Ensembles of Models -- 4.3 How to Select the Best Solutions for the Business Problem -- 4.3.1 Capabilities of Methods -- 4.3.2 Applicability of Methods -- 4.3.3 One Method Is Not Enough -- 4.4 Common Mistakes -- 4.4.1 Ignoring Integration of Methods -- 4.4.2 Lack of Knowledge of Strengths and Weaknesses of Methods -- 4.4.3 Lack of Knowledge about Selecting the Most Appropriate Methods for the Business Problem -- 4.5 Suggested Reading -- 4.6 Questions -- Chapter 5: The Lost-in-Translation Trap -- 5.1 Translation from Business Problems to Data Science Solutions -- 5.1.1 Select Best Experts in Problem Domain -- 5.1.2 Generic Problem Questionnaire Template -- 5.1.3 Problem Description by Domain Experts -- 5.1.4 Problem Understanding by Data Scientists -- 5.1.5 Create a Problem-Related Glossary -- 5.2 Translation from Data Science Solutions to Business Problems -- 5.2.1 Explain Data Science Work Process -- 5.2.2 Communicate Potential Data Science Solutions -- 5.2.3 Demonstrate Similar Data Science Use Cases -- 5.2.4 Explain Key Principles Related to Potential Data Science Solutions -- 5.2.5 Create a Solution-Related Glossary -- 5.3 Typical Lost-in-Translation Cases -- 5.3.1 Inexperienced Data Scientists -- 5.3.2 Resistance from Experts -- 5.3.3 Improper Problem Definition -- 5.3.4 Management Intervention -- 5.4 How to Avoid the-Lost-in-Translation Trap -- 5.4.1 Translators -- 5.4.2 Examples of Translators for AI-Methods -- 5.5 Common Mistakes -- 5.5.1 Ignoring the Dialog Between Domain Experts and Data Scientists -- 5.5.2 Ignoring the People Factor -- 5.5.3 Ignoring Team Building -- 5.6 Suggested Reading -- 5.7 Questions -- Part II: The AI-Based Data Science Toolbox -- Chapter 6: The AI-Based Data Science Workflow -- 6.1 Overview of Workflow</subfield></datafield><datafield tag="505" ind1="8" ind2=" "><subfield code="a">6.1.1 Why we Need an Effective AI-Based Data Science Workflow -- 6.1.2 Why Is the Classical Scientific Process Not Enough? -- 6.1.3 Comparison with CRISP-DM -- 6.1.4 AI-Based Data Science Workflow Sequence -- 6.2 Key Steps of AI-Based Data Science Workflow -- 6.2.1 Problem Definition -- 6.2.2 Project Organization -- 6.2.3 Problem Knowledge Acquisition -- 6.2.4 Data Preparation -- 6.2.5 Data Analysis -- 6.2.6 Model Development -- 6.2.7 Model Deployment -- 6.2.8 Model Maintenance -- 6.2.9 Automation of AI-Based Data Science Workflow -- 6.3 Project Organization -- 6.3.1 Organizing Project Teams -- 6.3.2 Resources Allocation -- 6.3.3 Project Scheduling -- 6.3.4 Project Funding -- 6.4 Common Mistakes -- 6.4.1 Ignoring a Detailed Workflow -- 6.4.2 Ignoring some Steps in the Workflow -- 6.4.3 Insufficient Efforts on Cost Estimates -- 6.4.4 Not Documenting the Deliverables -- 6.5 Suggested Reading -- 6.6 Questions -- Chapter 7: Problem Knowledge Acquisition -- 7.1 Importance of Problem Knowledge -- 7.1.1 Problem Knowledge in Problem Definition -- 7.1.2 Problem Knowledge in Data Preparation -- 7.1.3 Problem Knowledge in Data Analysis -- 7.1.4 Problem Knowledge in Model Development -- 7.1.5 Problem Knowledge in Model Deployment -- 7.2 Sources of Problem Knowledge -- 7.2.1 Subject Matter Experts -- 7.2.2 Problem-Related Documents -- 7.2.3 Publicly Available References -- 7.3 Problem Knowledge Acquisition Methods -- 7.3.1 Mind Mapping -- 7.3.2 Brainstorming Sessions -- 7.3.3 External Knowledge Acquisition -- 7.3.4 Knowledge Acquisition Skills -- 7.4 Problem Knowledge Integration -- 7.4.1 Define Recommended Assumptions -- 7.4.2 Define Normal/Abnormal Operating Conditions -- 7.4.3 Suggest Selection of Initial Variables -- 7.4.4 Define Qualitative Performance Metric -- 7.5 Definition of a Problem Solution Strategy -- 7.5.1 Define Solution Hypotheses</subfield></datafield><datafield tag="505" ind1="8" ind2=" "><subfield code="a">7.5.2 Define a List of Potential Solutions -- 7.5.3 Define Issues and Limitations of Suggested Solutions -- 7.5.4 Define Needed Infrastructure -- 7.6 Common Mistakes -- 7.6.1 Focusing on Data and Ignoring Problem Knowledge -- 7.6.2 SMEs Are Not Involved -- 7.6.3 Not Validating SMEs Knowledge -- 7.6.4 Reinventing the Wheel -- 7.7 Suggested Reading -- 7.8 Questions -- Chapter 8: Data Preparation -- 8.1 Data Collection -- 8.1.1 Data Sources -- 8.2 Visual Data Exploration -- 8.2.1 Strange Data Patterns -- 8.2.2 Data Distributions -- 8.2.3 Univariate Plots -- 8.2.4 Bivariate Plots -- 8.2.5 Multivariate Plots -- 8.3 Data Preprocessing -- 8.3.1 Handling Missing Data -- 8.3.2 Handling Outliers -- 8.3.3 Data Transformation -- 8.3.4 Data Balance -- 8.3.5 Data Quality Assessment -- 8.4 Common Mistakes -- 8.4.1 GIGO 2.0 -- 8.4.2 Problem Solving with Insufficient Data -- 8.4.3 Problem Solving with Low-Quality Data -- 8.4.4 Low-Quality Data Preparation -- 8.5 Suggested Reading -- 8.6 Questions -- Chapter 9: Data Analysis -- 9.1 Translation of Data into Insight -- 9.1.1 Problem Knowledge Gain from Data Analysis -- 9.1.2 Insight from Multivariate View -- 9.1.3 Insight from Understanding Key Drivers -- 9.1.4 Insight from Discovered Features and Patterns -- 9.1.5 Insight from Data Analysis as the Final Problem Solution -- 9.1.6 Insight for Final Data Preparation for Modeling -- 9.2 Multivariate Data Analysis -- 9.2.1 Principal Component Analysis -- 9.2.2 Multivariate Patterns -- 9.3 Variable Selection -- 9.3.1 Variable Reduction -- 9.3.2 Handling Multicollinearity -- 9.3.3 Linear Variable Selection -- 9.3.4 Nonlinear Variable Selection -- 9.4 Feature Extraction -- 9.4.1 Feature Engineering -- 9.4.2 Automatically Generated Features -- 9.5 Data Visualization -- 9.5.1 Parallel Coordinates Plot -- 9.5.2 Chord Diagram -- 9.5.3 Contour Plot</subfield></datafield><datafield tag="505" ind1="8" ind2=" "><subfield code="a">9.6 Data-Analysis-Driven Storytelling</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Artificial intelligence</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Business-Data processing</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Big data</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Big Data</subfield><subfield code="0">(DE-588)4802620-7</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="650" ind1="0" ind2="7"><subfield code="a">Künstliche Intelligenz</subfield><subfield code="0">(DE-588)4033447-8</subfield><subfield code="2">gnd</subfield><subfield code="9">rswk-swf</subfield></datafield><datafield tag="689" ind1="0" ind2="0"><subfield code="a">Künstliche Intelligenz</subfield><subfield code="0">(DE-588)4033447-8</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2="1"><subfield code="a">Big Data</subfield><subfield code="0">(DE-588)4802620-7</subfield><subfield code="D">s</subfield></datafield><datafield tag="689" ind1="0" ind2=" "><subfield code="5">DE-604</subfield></datafield><datafield tag="776" ind1="0" ind2="8"><subfield code="i">Erscheint auch als</subfield><subfield code="n">Druck-Ausgabe</subfield><subfield code="a">Kordon, Arthur K.</subfield><subfield code="t">Applying Data Science</subfield><subfield code="d">Cham : Springer International Publishing AG,c2020</subfield><subfield code="z">9783030363741</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">ZDB-30-PQE</subfield></datafield><datafield tag="999" ind1=" " ind2=" "><subfield code="a">oai:aleph.bib-bvb.de:BVB01-033604876</subfield></datafield></record></collection> |
| id | DE-604.BV048224143 |
| illustrated | Not Illustrated |
| index_date | 2024-07-03T19:50:39Z |
| indexdate | 2024-07-10T09:32:28Z |
| institution | BVB |
| isbn | 9783030363758 |
| language | English |
| oai_aleph_id | oai:aleph.bib-bvb.de:BVB01-033604876 |
| oclc_num | 1202483782 |
| open_access_boolean | |
| physical | 1 Online-Ressource (511 Seiten) |
| psigel | ZDB-30-PQE |
| publishDate | 2020 |
| publishDateSearch | 2020 |
| publishDateSort | 2020 |
| publisher | Springer International Publishing AG |
| record_format | marc |
| spelling | Kordon, Arthur K. Verfasser aut Applying Data Science How to Create Value with Artificial Intelligence Cham Springer International Publishing AG 2020 ©2020 1 Online-Ressource (511 Seiten) txt rdacontent c rdamedia cr rdacarrier Description based on publisher supplied metadata and other sources Intro -- Preface -- Motivation -- Purpose of the Book -- Who Is This Book for? -- How This Book Is Structured -- What This Book Is NOT About -- Features of the Book -- Acknowledgments -- Contents -- Part I: From Business Problems to Data Science -- Chapter 1: Data Science Based on Artificial Intelligence -- 1.1 Big Data, Big Mess, Big Opportunity -- 1.1.1 From Hype to Competitive Advantage -- 1.1.2 Key Buzzwords Explained -- 1.1.3 Why Now? -- 1.2 What Is AI-Based Data Science? -- 1.2.1 Definition of AI-Based Data Science -- 1.2.2 Features of AI-Based Data Science -- 1.3 Competitive Advantages of AI-Based Data Science -- 1.3.1 Creating ''Objective Intelligence'' -- 1.3.2 Dealing with Uncertainty -- 1.3.3 Dealing with Complexity -- 1.3.4 Generating Novelty -- 1.3.5 Low-Cost Modeling and Optimization -- 1.4 Key Challenges in Applying AI-Based Data Science -- 1.4.1 Technical Issues in Applying AI-Based Data Science -- 1.4.2 Nontechnical Issues in Applying AI-Based Data Science -- 1.5 Common Mistakes -- 1.5.1 Believing the Hype -- 1.5.2 Neglecting to Estimate the Demand for AI-Based Data Science -- 1.5.3 Mass-Scale Introduction of AI-Based Data Science in a Business without Required Skillset Availability -- 1.5.4 Introducing Data Science Bureaucracy -- 1.6 Suggested Reading -- 1.7 Questions -- Chapter 2: Business Problems Dependent on Data -- 2.1 The Leading Role of Business Problems -- 2.1.1 ''Data Is the New Oil'' Hype -- 2.1.2 Problems-First Approach -- 2.2 Typical Business Problems Related to AI-Based Data Science -- 2.2.1 Typical Problems in Manufacturing -- 2.2.2 Typical Problems in Business -- 2.3 How to Find Data-Driven Business Problems -- 2.3.1 Understand Business Needs -- 2.3.2 Match Business Needs with Known Artificial Intelligence-Based Use Cases -- 2.4 The Slippery Terrain of Problem Definition -- 2.4.1 Structure of Problem Definition 2.4.2 Example of Problem Definition -- 2.5 Value Creation Hypothesis -- 2.5.1 Sources of Value Creation -- 2.5.2 Metrics for Value Creation -- 2.6 Common Mistakes -- 2.6.1 Jumping to Solutions without Defining Business Problems -- 2.6.2 Neglecting the Importance of a Detailed Realistic Problem Definition -- 2.6.3 Ignoring Definition of Value Creation Metrics for the Problem -- 2.6.4 Believing in a Data First, Problems Second Approach -- 2.7 Suggested Reading -- 2.8 Questions -- Chapter 3: Artificial Intelligence-Based Data Science Solutions -- 3.1 Typical Solutions Related to Data Science -- 3.1.1 Prediction -- 3.1.2 Forecasting -- 3.1.3 Classification -- 3.1.4 Clustering -- 3.1.5 Optimization -- 3.1.6 Association -- 3.2 Advanced AI Solutions Related to Data Science -- 3.2.1 Natural Language Processing -- 3.2.2 Video/Image Processing -- 3.2.3 Sentiment Analysis -- 3.2.4 Artificial General Intelligence -- 3.3 Key AI Methods in a Nutshell -- 3.3.1 Neural Networks in a Nutshell -- 3.3.2 Deep Learning Networks in a Nutshell -- 3.3.3 Support Vector Machines in a Nutshell -- 3.3.4 Decision Trees in a Nutshell -- 3.3.5 Evolutionary Computation in a utshell -- 3.3.6 Swarm Intelligence in a Nutshell -- 3.3.7 Intelligent Agents in a Nutshell -- 3.4 Common Mistakes -- 3.4.1 Obsession with One Method -- 3.4.2 Focusing on Fashionable Methods -- 3.4.3 Lack of Knowledge about Broad Options for AI-Based Approaches -- 3.4.4 Lack of Knowledge about Cost of Implementation of Methods -- 3.5 Suggested Reading -- 3.6 Questions -- Chapter 4: Integrate and Conquer -- 4.1 The Integrate and Conquer Strategy in Applied Data Science -- 4.1.1 The Nasty Reality of Real-World Applications -- 4.1.2 Why Integration of Methods Is Critical for Real-World Applications -- 4.2 Integration Opportunities -- 4.2.1 Integration Between AI-Based Methods 4.2.2 Integration with First-Principles Models -- 4.2.3 Integration with Statistical Models -- 4.2.4 Integration by Ensembles of Models -- 4.3 How to Select the Best Solutions for the Business Problem -- 4.3.1 Capabilities of Methods -- 4.3.2 Applicability of Methods -- 4.3.3 One Method Is Not Enough -- 4.4 Common Mistakes -- 4.4.1 Ignoring Integration of Methods -- 4.4.2 Lack of Knowledge of Strengths and Weaknesses of Methods -- 4.4.3 Lack of Knowledge about Selecting the Most Appropriate Methods for the Business Problem -- 4.5 Suggested Reading -- 4.6 Questions -- Chapter 5: The Lost-in-Translation Trap -- 5.1 Translation from Business Problems to Data Science Solutions -- 5.1.1 Select Best Experts in Problem Domain -- 5.1.2 Generic Problem Questionnaire Template -- 5.1.3 Problem Description by Domain Experts -- 5.1.4 Problem Understanding by Data Scientists -- 5.1.5 Create a Problem-Related Glossary -- 5.2 Translation from Data Science Solutions to Business Problems -- 5.2.1 Explain Data Science Work Process -- 5.2.2 Communicate Potential Data Science Solutions -- 5.2.3 Demonstrate Similar Data Science Use Cases -- 5.2.4 Explain Key Principles Related to Potential Data Science Solutions -- 5.2.5 Create a Solution-Related Glossary -- 5.3 Typical Lost-in-Translation Cases -- 5.3.1 Inexperienced Data Scientists -- 5.3.2 Resistance from Experts -- 5.3.3 Improper Problem Definition -- 5.3.4 Management Intervention -- 5.4 How to Avoid the-Lost-in-Translation Trap -- 5.4.1 Translators -- 5.4.2 Examples of Translators for AI-Methods -- 5.5 Common Mistakes -- 5.5.1 Ignoring the Dialog Between Domain Experts and Data Scientists -- 5.5.2 Ignoring the People Factor -- 5.5.3 Ignoring Team Building -- 5.6 Suggested Reading -- 5.7 Questions -- Part II: The AI-Based Data Science Toolbox -- Chapter 6: The AI-Based Data Science Workflow -- 6.1 Overview of Workflow 6.1.1 Why we Need an Effective AI-Based Data Science Workflow -- 6.1.2 Why Is the Classical Scientific Process Not Enough? -- 6.1.3 Comparison with CRISP-DM -- 6.1.4 AI-Based Data Science Workflow Sequence -- 6.2 Key Steps of AI-Based Data Science Workflow -- 6.2.1 Problem Definition -- 6.2.2 Project Organization -- 6.2.3 Problem Knowledge Acquisition -- 6.2.4 Data Preparation -- 6.2.5 Data Analysis -- 6.2.6 Model Development -- 6.2.7 Model Deployment -- 6.2.8 Model Maintenance -- 6.2.9 Automation of AI-Based Data Science Workflow -- 6.3 Project Organization -- 6.3.1 Organizing Project Teams -- 6.3.2 Resources Allocation -- 6.3.3 Project Scheduling -- 6.3.4 Project Funding -- 6.4 Common Mistakes -- 6.4.1 Ignoring a Detailed Workflow -- 6.4.2 Ignoring some Steps in the Workflow -- 6.4.3 Insufficient Efforts on Cost Estimates -- 6.4.4 Not Documenting the Deliverables -- 6.5 Suggested Reading -- 6.6 Questions -- Chapter 7: Problem Knowledge Acquisition -- 7.1 Importance of Problem Knowledge -- 7.1.1 Problem Knowledge in Problem Definition -- 7.1.2 Problem Knowledge in Data Preparation -- 7.1.3 Problem Knowledge in Data Analysis -- 7.1.4 Problem Knowledge in Model Development -- 7.1.5 Problem Knowledge in Model Deployment -- 7.2 Sources of Problem Knowledge -- 7.2.1 Subject Matter Experts -- 7.2.2 Problem-Related Documents -- 7.2.3 Publicly Available References -- 7.3 Problem Knowledge Acquisition Methods -- 7.3.1 Mind Mapping -- 7.3.2 Brainstorming Sessions -- 7.3.3 External Knowledge Acquisition -- 7.3.4 Knowledge Acquisition Skills -- 7.4 Problem Knowledge Integration -- 7.4.1 Define Recommended Assumptions -- 7.4.2 Define Normal/Abnormal Operating Conditions -- 7.4.3 Suggest Selection of Initial Variables -- 7.4.4 Define Qualitative Performance Metric -- 7.5 Definition of a Problem Solution Strategy -- 7.5.1 Define Solution Hypotheses 7.5.2 Define a List of Potential Solutions -- 7.5.3 Define Issues and Limitations of Suggested Solutions -- 7.5.4 Define Needed Infrastructure -- 7.6 Common Mistakes -- 7.6.1 Focusing on Data and Ignoring Problem Knowledge -- 7.6.2 SMEs Are Not Involved -- 7.6.3 Not Validating SMEs Knowledge -- 7.6.4 Reinventing the Wheel -- 7.7 Suggested Reading -- 7.8 Questions -- Chapter 8: Data Preparation -- 8.1 Data Collection -- 8.1.1 Data Sources -- 8.2 Visual Data Exploration -- 8.2.1 Strange Data Patterns -- 8.2.2 Data Distributions -- 8.2.3 Univariate Plots -- 8.2.4 Bivariate Plots -- 8.2.5 Multivariate Plots -- 8.3 Data Preprocessing -- 8.3.1 Handling Missing Data -- 8.3.2 Handling Outliers -- 8.3.3 Data Transformation -- 8.3.4 Data Balance -- 8.3.5 Data Quality Assessment -- 8.4 Common Mistakes -- 8.4.1 GIGO 2.0 -- 8.4.2 Problem Solving with Insufficient Data -- 8.4.3 Problem Solving with Low-Quality Data -- 8.4.4 Low-Quality Data Preparation -- 8.5 Suggested Reading -- 8.6 Questions -- Chapter 9: Data Analysis -- 9.1 Translation of Data into Insight -- 9.1.1 Problem Knowledge Gain from Data Analysis -- 9.1.2 Insight from Multivariate View -- 9.1.3 Insight from Understanding Key Drivers -- 9.1.4 Insight from Discovered Features and Patterns -- 9.1.5 Insight from Data Analysis as the Final Problem Solution -- 9.1.6 Insight for Final Data Preparation for Modeling -- 9.2 Multivariate Data Analysis -- 9.2.1 Principal Component Analysis -- 9.2.2 Multivariate Patterns -- 9.3 Variable Selection -- 9.3.1 Variable Reduction -- 9.3.2 Handling Multicollinearity -- 9.3.3 Linear Variable Selection -- 9.3.4 Nonlinear Variable Selection -- 9.4 Feature Extraction -- 9.4.1 Feature Engineering -- 9.4.2 Automatically Generated Features -- 9.5 Data Visualization -- 9.5.1 Parallel Coordinates Plot -- 9.5.2 Chord Diagram -- 9.5.3 Contour Plot 9.6 Data-Analysis-Driven Storytelling Artificial intelligence Business-Data processing Big data Big Data (DE-588)4802620-7 gnd rswk-swf Künstliche Intelligenz (DE-588)4033447-8 gnd rswk-swf Künstliche Intelligenz (DE-588)4033447-8 s Big Data (DE-588)4802620-7 s DE-604 Erscheint auch als Druck-Ausgabe Kordon, Arthur K. Applying Data Science Cham : Springer International Publishing AG,c2020 9783030363741 |
| spellingShingle | Kordon, Arthur K. Applying Data Science How to Create Value with Artificial Intelligence Intro -- Preface -- Motivation -- Purpose of the Book -- Who Is This Book for? -- How This Book Is Structured -- What This Book Is NOT About -- Features of the Book -- Acknowledgments -- Contents -- Part I: From Business Problems to Data Science -- Chapter 1: Data Science Based on Artificial Intelligence -- 1.1 Big Data, Big Mess, Big Opportunity -- 1.1.1 From Hype to Competitive Advantage -- 1.1.2 Key Buzzwords Explained -- 1.1.3 Why Now? -- 1.2 What Is AI-Based Data Science? -- 1.2.1 Definition of AI-Based Data Science -- 1.2.2 Features of AI-Based Data Science -- 1.3 Competitive Advantages of AI-Based Data Science -- 1.3.1 Creating ''Objective Intelligence'' -- 1.3.2 Dealing with Uncertainty -- 1.3.3 Dealing with Complexity -- 1.3.4 Generating Novelty -- 1.3.5 Low-Cost Modeling and Optimization -- 1.4 Key Challenges in Applying AI-Based Data Science -- 1.4.1 Technical Issues in Applying AI-Based Data Science -- 1.4.2 Nontechnical Issues in Applying AI-Based Data Science -- 1.5 Common Mistakes -- 1.5.1 Believing the Hype -- 1.5.2 Neglecting to Estimate the Demand for AI-Based Data Science -- 1.5.3 Mass-Scale Introduction of AI-Based Data Science in a Business without Required Skillset Availability -- 1.5.4 Introducing Data Science Bureaucracy -- 1.6 Suggested Reading -- 1.7 Questions -- Chapter 2: Business Problems Dependent on Data -- 2.1 The Leading Role of Business Problems -- 2.1.1 ''Data Is the New Oil'' Hype -- 2.1.2 Problems-First Approach -- 2.2 Typical Business Problems Related to AI-Based Data Science -- 2.2.1 Typical Problems in Manufacturing -- 2.2.2 Typical Problems in Business -- 2.3 How to Find Data-Driven Business Problems -- 2.3.1 Understand Business Needs -- 2.3.2 Match Business Needs with Known Artificial Intelligence-Based Use Cases -- 2.4 The Slippery Terrain of Problem Definition -- 2.4.1 Structure of Problem Definition 2.4.2 Example of Problem Definition -- 2.5 Value Creation Hypothesis -- 2.5.1 Sources of Value Creation -- 2.5.2 Metrics for Value Creation -- 2.6 Common Mistakes -- 2.6.1 Jumping to Solutions without Defining Business Problems -- 2.6.2 Neglecting the Importance of a Detailed Realistic Problem Definition -- 2.6.3 Ignoring Definition of Value Creation Metrics for the Problem -- 2.6.4 Believing in a Data First, Problems Second Approach -- 2.7 Suggested Reading -- 2.8 Questions -- Chapter 3: Artificial Intelligence-Based Data Science Solutions -- 3.1 Typical Solutions Related to Data Science -- 3.1.1 Prediction -- 3.1.2 Forecasting -- 3.1.3 Classification -- 3.1.4 Clustering -- 3.1.5 Optimization -- 3.1.6 Association -- 3.2 Advanced AI Solutions Related to Data Science -- 3.2.1 Natural Language Processing -- 3.2.2 Video/Image Processing -- 3.2.3 Sentiment Analysis -- 3.2.4 Artificial General Intelligence -- 3.3 Key AI Methods in a Nutshell -- 3.3.1 Neural Networks in a Nutshell -- 3.3.2 Deep Learning Networks in a Nutshell -- 3.3.3 Support Vector Machines in a Nutshell -- 3.3.4 Decision Trees in a Nutshell -- 3.3.5 Evolutionary Computation in a utshell -- 3.3.6 Swarm Intelligence in a Nutshell -- 3.3.7 Intelligent Agents in a Nutshell -- 3.4 Common Mistakes -- 3.4.1 Obsession with One Method -- 3.4.2 Focusing on Fashionable Methods -- 3.4.3 Lack of Knowledge about Broad Options for AI-Based Approaches -- 3.4.4 Lack of Knowledge about Cost of Implementation of Methods -- 3.5 Suggested Reading -- 3.6 Questions -- Chapter 4: Integrate and Conquer -- 4.1 The Integrate and Conquer Strategy in Applied Data Science -- 4.1.1 The Nasty Reality of Real-World Applications -- 4.1.2 Why Integration of Methods Is Critical for Real-World Applications -- 4.2 Integration Opportunities -- 4.2.1 Integration Between AI-Based Methods 4.2.2 Integration with First-Principles Models -- 4.2.3 Integration with Statistical Models -- 4.2.4 Integration by Ensembles of Models -- 4.3 How to Select the Best Solutions for the Business Problem -- 4.3.1 Capabilities of Methods -- 4.3.2 Applicability of Methods -- 4.3.3 One Method Is Not Enough -- 4.4 Common Mistakes -- 4.4.1 Ignoring Integration of Methods -- 4.4.2 Lack of Knowledge of Strengths and Weaknesses of Methods -- 4.4.3 Lack of Knowledge about Selecting the Most Appropriate Methods for the Business Problem -- 4.5 Suggested Reading -- 4.6 Questions -- Chapter 5: The Lost-in-Translation Trap -- 5.1 Translation from Business Problems to Data Science Solutions -- 5.1.1 Select Best Experts in Problem Domain -- 5.1.2 Generic Problem Questionnaire Template -- 5.1.3 Problem Description by Domain Experts -- 5.1.4 Problem Understanding by Data Scientists -- 5.1.5 Create a Problem-Related Glossary -- 5.2 Translation from Data Science Solutions to Business Problems -- 5.2.1 Explain Data Science Work Process -- 5.2.2 Communicate Potential Data Science Solutions -- 5.2.3 Demonstrate Similar Data Science Use Cases -- 5.2.4 Explain Key Principles Related to Potential Data Science Solutions -- 5.2.5 Create a Solution-Related Glossary -- 5.3 Typical Lost-in-Translation Cases -- 5.3.1 Inexperienced Data Scientists -- 5.3.2 Resistance from Experts -- 5.3.3 Improper Problem Definition -- 5.3.4 Management Intervention -- 5.4 How to Avoid the-Lost-in-Translation Trap -- 5.4.1 Translators -- 5.4.2 Examples of Translators for AI-Methods -- 5.5 Common Mistakes -- 5.5.1 Ignoring the Dialog Between Domain Experts and Data Scientists -- 5.5.2 Ignoring the People Factor -- 5.5.3 Ignoring Team Building -- 5.6 Suggested Reading -- 5.7 Questions -- Part II: The AI-Based Data Science Toolbox -- Chapter 6: The AI-Based Data Science Workflow -- 6.1 Overview of Workflow 6.1.1 Why we Need an Effective AI-Based Data Science Workflow -- 6.1.2 Why Is the Classical Scientific Process Not Enough? -- 6.1.3 Comparison with CRISP-DM -- 6.1.4 AI-Based Data Science Workflow Sequence -- 6.2 Key Steps of AI-Based Data Science Workflow -- 6.2.1 Problem Definition -- 6.2.2 Project Organization -- 6.2.3 Problem Knowledge Acquisition -- 6.2.4 Data Preparation -- 6.2.5 Data Analysis -- 6.2.6 Model Development -- 6.2.7 Model Deployment -- 6.2.8 Model Maintenance -- 6.2.9 Automation of AI-Based Data Science Workflow -- 6.3 Project Organization -- 6.3.1 Organizing Project Teams -- 6.3.2 Resources Allocation -- 6.3.3 Project Scheduling -- 6.3.4 Project Funding -- 6.4 Common Mistakes -- 6.4.1 Ignoring a Detailed Workflow -- 6.4.2 Ignoring some Steps in the Workflow -- 6.4.3 Insufficient Efforts on Cost Estimates -- 6.4.4 Not Documenting the Deliverables -- 6.5 Suggested Reading -- 6.6 Questions -- Chapter 7: Problem Knowledge Acquisition -- 7.1 Importance of Problem Knowledge -- 7.1.1 Problem Knowledge in Problem Definition -- 7.1.2 Problem Knowledge in Data Preparation -- 7.1.3 Problem Knowledge in Data Analysis -- 7.1.4 Problem Knowledge in Model Development -- 7.1.5 Problem Knowledge in Model Deployment -- 7.2 Sources of Problem Knowledge -- 7.2.1 Subject Matter Experts -- 7.2.2 Problem-Related Documents -- 7.2.3 Publicly Available References -- 7.3 Problem Knowledge Acquisition Methods -- 7.3.1 Mind Mapping -- 7.3.2 Brainstorming Sessions -- 7.3.3 External Knowledge Acquisition -- 7.3.4 Knowledge Acquisition Skills -- 7.4 Problem Knowledge Integration -- 7.4.1 Define Recommended Assumptions -- 7.4.2 Define Normal/Abnormal Operating Conditions -- 7.4.3 Suggest Selection of Initial Variables -- 7.4.4 Define Qualitative Performance Metric -- 7.5 Definition of a Problem Solution Strategy -- 7.5.1 Define Solution Hypotheses 7.5.2 Define a List of Potential Solutions -- 7.5.3 Define Issues and Limitations of Suggested Solutions -- 7.5.4 Define Needed Infrastructure -- 7.6 Common Mistakes -- 7.6.1 Focusing on Data and Ignoring Problem Knowledge -- 7.6.2 SMEs Are Not Involved -- 7.6.3 Not Validating SMEs Knowledge -- 7.6.4 Reinventing the Wheel -- 7.7 Suggested Reading -- 7.8 Questions -- Chapter 8: Data Preparation -- 8.1 Data Collection -- 8.1.1 Data Sources -- 8.2 Visual Data Exploration -- 8.2.1 Strange Data Patterns -- 8.2.2 Data Distributions -- 8.2.3 Univariate Plots -- 8.2.4 Bivariate Plots -- 8.2.5 Multivariate Plots -- 8.3 Data Preprocessing -- 8.3.1 Handling Missing Data -- 8.3.2 Handling Outliers -- 8.3.3 Data Transformation -- 8.3.4 Data Balance -- 8.3.5 Data Quality Assessment -- 8.4 Common Mistakes -- 8.4.1 GIGO 2.0 -- 8.4.2 Problem Solving with Insufficient Data -- 8.4.3 Problem Solving with Low-Quality Data -- 8.4.4 Low-Quality Data Preparation -- 8.5 Suggested Reading -- 8.6 Questions -- Chapter 9: Data Analysis -- 9.1 Translation of Data into Insight -- 9.1.1 Problem Knowledge Gain from Data Analysis -- 9.1.2 Insight from Multivariate View -- 9.1.3 Insight from Understanding Key Drivers -- 9.1.4 Insight from Discovered Features and Patterns -- 9.1.5 Insight from Data Analysis as the Final Problem Solution -- 9.1.6 Insight for Final Data Preparation for Modeling -- 9.2 Multivariate Data Analysis -- 9.2.1 Principal Component Analysis -- 9.2.2 Multivariate Patterns -- 9.3 Variable Selection -- 9.3.1 Variable Reduction -- 9.3.2 Handling Multicollinearity -- 9.3.3 Linear Variable Selection -- 9.3.4 Nonlinear Variable Selection -- 9.4 Feature Extraction -- 9.4.1 Feature Engineering -- 9.4.2 Automatically Generated Features -- 9.5 Data Visualization -- 9.5.1 Parallel Coordinates Plot -- 9.5.2 Chord Diagram -- 9.5.3 Contour Plot 9.6 Data-Analysis-Driven Storytelling Artificial intelligence Business-Data processing Big data Big Data (DE-588)4802620-7 gnd Künstliche Intelligenz (DE-588)4033447-8 gnd |
| subject_GND | (DE-588)4802620-7 (DE-588)4033447-8 |
| title | Applying Data Science How to Create Value with Artificial Intelligence |
| title_auth | Applying Data Science How to Create Value with Artificial Intelligence |
| title_exact_search | Applying Data Science How to Create Value with Artificial Intelligence |
| title_exact_search_txtP | Applying Data Science How to Create Value with Artificial Intelligence |
| title_full | Applying Data Science How to Create Value with Artificial Intelligence |
| title_fullStr | Applying Data Science How to Create Value with Artificial Intelligence |
| title_full_unstemmed | Applying Data Science How to Create Value with Artificial Intelligence |
| title_short | Applying Data Science |
| title_sort | applying data science how to create value with artificial intelligence |
| title_sub | How to Create Value with Artificial Intelligence |
| topic | Artificial intelligence Business-Data processing Big data Big Data (DE-588)4802620-7 gnd Künstliche Intelligenz (DE-588)4033447-8 gnd |
| topic_facet | Artificial intelligence Business-Data processing Big data Big Data Künstliche Intelligenz |
| work_keys_str_mv | AT kordonarthurk applyingdatasciencehowtocreatevaluewithartificialintelligence |