Recommender System for Improving Customer Loyalty (eBook)

Katarzyna Tarnowska, Zbigniew W. Ras, Lynn Daniel (Autoren)

eBook Download: PDF

2019 | 1st ed. 2020
XVIII, 124 Seiten
Springer International Publishing (Verlag)
978-3-030-13438-9 (ISBN)

Infos

This book presents the Recommender System for Improving Customer Loyalty. New and innovative products have begun appearing from a wide variety of countries, which has increased the need to improve the customer experience. When a customer spends hundreds of thousands of dollars on a piece of equipment, keeping it running efficiently is critical to achieving the desired return on investment. Moreover, managers have discovered that delivering a better customer experience pays off in a number of ways. A study of publicly traded companies conducted by Watermark Consulting found that from 2007 to 2013, companies with a better customer service generated a total return to shareholders that was 26 points higher than the S&P 500. This is only one of many studies that illustrate the measurable value of providing a better service experience.

The Recommender System presented here addresses several important issues. (1) It provides a decision framework to help managers determine which actions are likely to have the greatest impact on the Net Promoter Score. (2) The results are based on multiple clients. The data mining techniques employed in the Recommender System allow users to 'learn' from the experiences of others, without sharing proprietary information. This dramatically enhances the power of the system. (3) It supplements traditional text mining options. Text mining can be used to identify the frequency with which topics are mentioned, and the sentiment associated with a given topic. The Recommender System allows users to view specific, anonymous comments associated with actual customers. Studying these comments can provide highly accurate insights into the steps that can be taken to improve the customer experience. (4) Lastly, the system provides a sensitivity analysis feature. In some cases, certain actions can be more easily implemented than others. The Recommender System allows managers to 'weigh' these actions and determine which ones would have a greater impact.

Inhalt

Preface 6
About the Book 7
Contents 8
List of Figures 12
List of Tables 15
1 Introduction 17
1.1 Why Customer Experience Matters More Now? 17
1.2 Top (and Bottom) Line Reasons for Better Customer Experience 19
1.3 What is Next? 21
1.4 Final Observations 21
2 Customer Loyalty Improvement 23
2.1 Introduction to the Problem Area 23
2.2 Dataset Description 24
2.3 Decision Problem 25
2.4 Problem Area 25
2.4.1 Attribute Analysis 25
2.4.2 Attribute Reduction 26
2.4.3 Customer Satisfaction Analysis and Recognition 26
2.4.4 Providing Recommendations 27
Reference 27
3 State of the Art 28
3.1 Customer Satisfaction Software Tools 28
3.2 Customer Relationship Management Systems 29
3.3 Decision Support Systems 29
3.4 Recommender Systems 29
3.4.1 Recommender Systems for B2B 30
3.4.2 Types of Recommender Systems 31
3.4.3 Knowledge Based Approach for Recommendation 32
3.5 Text Analytics and Sentiment Analysis Tools 32
References 33
4 Background 35
4.1 Knowledge Discovery 35
4.1.1 Decision Reducts 35
4.1.2 Classification 37
4.1.3 Action Rules 38
4.1.4 Clustering 40
4.2 Text Mining 40
4.2.1 Sentiment Analysis 40
4.2.2 Aspect-Based Sentiment Analysis 41
4.2.3 Aspect Extraction 43
4.2.4 Polarity Calculation 45
4.2.5 Natural Language Processing Issues 46
4.2.6 Summary Generation 46
4.2.7 Visualizations 47
4.2.8 Measuring the Economic Impact of Sentiment 49
References 51
5 Overview of Recommender System Engine 54
5.1 High-Level Architecture 54
5.2 Data Preparation 56
5.2.1 Raw Data Import 56
5.2.2 Data Preprocessing 58
5.3 Semantic Similarity 62
5.4 Hierarchical Agglomerative Method for Improving NPS 64
5.5 Action Rules 66
5.6 Meta Actions and Triggering Mechanism 67
5.7 Text Mining 68
References 70
6 Visual Data Analysis 71
6.1 Decision Reducts as Heatmap 71
6.2 Classification Visualizations: Dual Scale Bar Chart and Confusion Matrix 73
6.3 Multiple Views 74
6.4 Evaluation Results 74
6.4.1 Single Client Data (Local) Analysis 75
6.4.2 Global Customer Sentiment Analysis and Prediction 76
6.5 User-Friendly Interface for the Recommender System 77
7 Improving Performance of Knowledge Miner 80
7.1 Introduction 80
7.2 Problem Statement 80
7.3 Assumptions 81
7.4 Strategy and Overall Approach 82
7.5 Evaluation 84
7.5.1 Experimental Setup 84
7.5.2 Results 85
7.5.3 New Rule Format in RS 89
7.6 Plans for Remaining Challenges 96
Reference 96
8 Recommender System Based on Unstructured Data 97
8.1 Introduction 97
8.2 Problem Statement 97
8.3 Assumptions 97
8.4 Strategy and Overall Approach 99
8.4.1 Data Transformation 99
8.4.2 Action Rule Mining 100
8.4.3 Ideas for the Improvement of Opinion Mining 101
8.4.4 Sentiment Extraction 101
8.4.5 Polarity Calculation 102
8.5 Evaluation 103
8.5.1 Initial Experiments 103
8.5.2 Experimental Setup 103
8.5.3 Improving Sentiment Analysis Algorithm 104
8.5.4 Experimental Results 108
8.5.5 Modified Algorithm for Opinion Mining 110
8.5.6 Comparing Recommendations with the Previous Approach 112
8.6 Plans for Remaining Challenges 116
8.6.1 Complex and Comparative Sentences 117
8.6.2 Implicit Opinions 118
8.6.3 Feature and Opinion in One Word 118
8.6.4 Opinion Words in Different Context 119
8.6.5 Ambiguity 119
8.6.6 Misspellings 120
8.6.7 Phrases, Idiomatic and Phrasal Verbs Expressions 120
8.6.8 Entity Recognition From Pronouns and Names 120
References 121
9 Customer Attrition Problem 122
9.1 Introduction 122
9.2 Problem Statement 122
9.3 Assumptions 124
9.4 Strategy and Overall Approach 124
9.4.1 Automatic Data Labelling 124
9.4.2 Pattern Mining 125
9.4.3 Sequence Mining 126
9.4.4 Action Rule, Meta Action Mining and Triggering 126
9.5 Evaluation 126
9.5.1 Initial Data Analysis 127
9.5.2 Attribute Selection 127
9.5.3 Classification Model 128
9.5.4 Action Rule Mining 129
9.6 Plans for Remaining Challenges 131
Reference 131
10 Conclusions 132
10.1 Contribution 132
10.2 Future Work 133

Produkt-Details

• Erscheint lt. Verlag: 19.3.2019
• Reihe/Serie: Studies in Big Data
• Reihe/Serie: Studies in Big Data
• Zusatzinfo: XVIII, 124 p. 40 illus., 30 illus. in color.
• Verlagsort: Cham
• Sprache: englisch
• Themenwelt: Mathematik / Informatik ► Informatik ► Datenbanken
• Themenwelt: Technik
• Themenwelt: Wirtschaft
• Schlagworte: actionable knowledge • Big Data • CLIRS • Computational Intelligence • Customer Loyalty Improvement Recommender System • Customer Retention • Meta-action Retraction • Recommendation from Action Rules • Recommender Systems • sentiment analysis
• ISBN-10: 3-030-13438-5 / 3030134385
• ISBN-13: 978-3-030-13438-9 / 9783030134389