Proactive Data Mining with Decision Trees (eBook)
X, 88 Seiten
Springer New York (Verlag)
978-1-4939-0539-3 (ISBN)
This book explores a proactive and domain-driven method to classification tasks. This novel proactive approach to data mining not only induces a model for predicting or explaining a phenomenon, but also utilizes specific problem/domain knowledge to suggest specific actions to achieve optimal changes in the value of the target attribute. In particular, the authors suggest a specific implementation of the domain-driven proactive approach for classification trees. The book centers on the core idea of moving observations from one branch of the tree to another. It introduces a novel splitting criterion for decision trees, termed maximal-utility, which maximizes the potential for enhancing profitability in the output tree. Two real-world case studies, one of a leading wireless operator and the other of a major security company, are also included and demonstrate how applying the proactive approach to classification tasks can solve business problems. Proactive Data Mining with Decision Trees is intended for researchers, practitioners and advanced-level students.
Preface 6
Contents 8
Chapter 1 Introduction to Proactive Data Mining 10
1.1 Data Mining 10
1.2 Classification Tasks 10
1.3 Basic Terms 11
1.3.1 Training Set 11
1.3.2 Classification Task 11
1.3.3 Induction Algorithm 12
1.4 Decision Trees (Classification Trees) 12
1.5 Cost Sensitive Classification Trees 15
1.6 Classification Trees Limitations 17
1.7 Active Learning 17
1.8 Actionable Data Mining 19
1.9 Human Cooperated Mining 20
References 21
Chapter 2 Proactive Data Mining: A General Approach and Algorithmic Framework 24
2.1 Notations 24
2.2 From Passive to Proactive Data Mining 25
2.3 Changing the Input Data 26
2.4 The Need for Domain Knowledge: Attribute Changing Cost and Benefit Functions 27
2.5 Maximal Utility: The Objective of Proactive Data Mining Tasks 27
2.6 An Algorithmic Framework for Proactive Data Mining 28
2.7 Chapter Summary 29
References 29
Chapter 3 Proactive Data Mining Using Decision Trees 30
3.1 Why Decision Trees? 30
3.2 The Utility Measure of Proactive Decision Trees 31
3.3 An Optimization Algorithm for Proactive Decision Trees 35
3.4 The Maximal-Utility Splitting Criterion 36
3.5 Chapter Summary 40
References 42
Chapter 4 Proactive Data Mining in the Real World: Case Studies 43
4.1 Proactive Data Mining in a Cellular Service Provider 43
4.1.1 The Data Mining Problem for the Wireless Company 43
4.1.2 The Wireless Dataset 44
4.1.3 Attribute Discretization 45
4.1.4 Additional Environment and Problem Knowledge for the Wireless Company 46
4.1.4.1 Cost Matrices 47
4.1.4.2 Benefit Matrix 49
4.1.5 Passive Classification Model for the Wireless Company 50
4.1.6 Maximal Utility Generated Model for the Wireless Company 51
4.1.7 Optimization Algorithm over the J48 Generated Model for the Wireless Company 54
4.1.8 Optimization Algorithm over the Maximal Utility Generated Model for the Wireless Company 54
4.2 The Security Company Case 56
4.2.1 The Data Mining Problem for the Security Company 57
4.2.2 The Security Dataset 58
4.2.3 Attribute Discretization 59
4.2.4 Additional Environment and Problem Knowledge for the Security Company 60
4.2.4.1 Cost Matrices 60
4.2.4.2 Benefit Matrix 62
4.2.5 Passive Classification Model for the Security Company 63
4.2.6 Maximal Utility Generated Model for the Security Company 63
4.2.7 Optimization Algorithm over the J48 Generated Model for the Security Company 64
4.2.8 Optimization Algorithm over the Maximal Utility Generated Model for the Security Company 66
4.3 Case Studies Summary 68
References 69
Chapter 5 Sensitivity Analysis of Proactive Data Mining 70
5.1 Zero-one Benefit Function 70
5.2 Dynamic Benefit Function 76
5.3 Dynamic Benefits and Infinite Costs of the Unchangeable Attributes 78
5.4 Dynamic Benefit and Balanced Cost Functions 83
5.5 Chapter Summary 91
References 91
Chapter 6 Conclusions 93
| Erscheint lt. Verlag | 14.2.2014 |
|---|---|
| Reihe/Serie | SpringerBriefs in Electrical and Computer Engineering | SpringerBriefs in Electrical and Computer Engineering |
| Zusatzinfo | X, 88 p. 20 illus. |
| Verlagsort | New York |
| Sprache | englisch |
| Themenwelt | Informatik ► Datenbanken ► Data Warehouse / Data Mining |
| Mathematik / Informatik ► Mathematik ► Statistik | |
| Technik | |
| Schlagworte | Active learning • Data Mining • decision trees • maximal-utility splitting criterion • Optimization |
| ISBN-10 | 1-4939-0539-2 / 1493905392 |
| ISBN-13 | 978-1-4939-0539-3 / 9781493905393 |
| Haben Sie eine Frage zum Produkt? |
PDF (Wasserzeichen)Größe: 2,2 MB
DRM: Digitales Wasserzeichen
Dieses eBook enthält ein digitales Wasserzeichen und ist damit für Sie personalisiert. Bei einer missbräuchlichen Weitergabe des eBooks an Dritte ist eine Rückverfolgung an die Quelle möglich.
Dateiformat: PDF (Portable Document Format)
Mit einem festen Seitenlayout eignet sich die PDF besonders für Fachbücher mit Spalten, Tabellen und Abbildungen. Eine PDF kann auf fast allen Geräten angezeigt werden, ist aber für kleine Displays (Smartphone, eReader) nur eingeschränkt geeignet.
Systemvoraussetzungen:
PC/Mac: Mit einem PC oder Mac können Sie dieses eBook lesen. Sie benötigen dafür einen PDF-Viewer - z.B. den Adobe Reader oder Adobe Digital Editions.
eReader: Dieses eBook kann mit (fast) allen eBook-Readern gelesen werden. Mit dem amazon-Kindle ist es aber nicht kompatibel.
Smartphone/Tablet: Egal ob Apple oder Android, dieses eBook können Sie lesen. Sie benötigen dafür einen PDF-Viewer - z.B. die kostenlose Adobe Digital Editions-App.
Zusätzliches Feature: Online Lesen
Dieses eBook können Sie zusätzlich zum Download auch online im Webbrowser lesen.
Buying eBooks from abroad
For tax law reasons we can sell eBooks just within Germany and Switzerland. Regrettably we cannot fulfill eBook-orders from other countries.
aus dem Bereich
