Data-Driven Process Discovery and Analysis: Third IFIP WG 2. 6, 2. 12 International Symposium, SIMPDA 2013, Riva Del Garda, Italy, August 30, 2013, Revised Selected Papers

This book constitutes the thoroughly refereed proceedings of the Third International Symposium on Data-Driven Process Discovery and Analysis held in Riva del Garda, Italy, in August 2013. The six revised full papers were carefully selected from 18 submissions. Following the event, authors were given the opportunity to improve their papers with the insights they gained from the symposium. The selected papers cover theoretical issues related to process representation, discovery and analysis or provide practical and operational experiences in process discovery and analysis. Preface 6 Organization 8 Contents 10 The Effect of Noise on Mined Declarative Constraints 11 1 Introduction 11 2 Declare Constraints 12 2.1 Declare Constraint Templates as FOL Formulae 14 3 Constraints' Properties 16 3.1 How Constraints Affect the Activities 16 3.2 Constraints' Interdependencies 17 4 Hypotheses on the Reaction of Constraints to Noise 20 5 Evaluation 20 5.1 Noise Categories 21 5.2 Experiment Setup 21 5.3 Participation (H1) 22 5.4 AtMostOne (H2) 23 5.5 Init and End (H3) 23 5.6 Response (H4, H5) 23 5.7 Precedence (H6, H7) 24 5.8 Succession (H8) 24 5.9 NotCoExistence (H9) 25 5.10 The Restriction Hierarchy Under CoExistence (H10) 27 5.11 Summary of Experiments 29 6 Related Work 29 7 Conclusion 31 References 31 Towards Collecting Sustainability Data in Supply Chains with Flexible Data Collection Processes 35 1 Introduction 35 2 Sustainable Supply Chains 36 2.1 Fundamentals 36 2.2 Illustrating Example 37 3 Data Collection Challenges 39 3.1 DCC 1: Dynamic Selection of Involved Parties 39 3.2 DCC 2: Access to Requested Data 40 3.3 DCC 3: Meta Data Management 41 3.4 DCC 4: Request Variants 41 3.5 DCC 5: Incompleteness and Quality 42 3.6 DCC 6: Monitoring 43 3.7 DCC 7: Run Time Variability 43 4 State of the Art 44 4.1 Process Configuration 45 4.2 Data- and User-Driven Processes 46 4.3 Dynamic Processes 47 5 Data Collection with Adaptive Processes 47 5.1 Configuration of Data Collection Processes 49 5.2 Adaptation of Data Collection Processes 51 5.3 Monitoring and Data Quality of Data Collection Processes 52 6 Conclusion 54 References 55 Handling Environment for Publicly Posted Composite Documents 58 1 Introduction 58 2 State of the Art 59 3 PPCD Structure and Access Procedures 60 4 Problem Statement 61 5 Our Solution 62 5.1 High Level Overview 62 5.2 Creating and Accessing PPCD 64 5.3 PPCD Integrity 67 5.4 Extension to Other Operating Systems 71 6 Current Prototype and Implementation 71 7 Conclusions and Future Work 72 Enabling Non-expert Users to Apply Data Mining for Bridging the Big Data Divide 75 1 Introduction 75 2 Related Work 77 3 Knowledge-Based Approach for Enabling Non-expert Users to Apply Data Mining 78 3.1 Allowing Non-experts to Specify Data Mining Requirements 78 3.2 Data Mining Knowledge Base 80 3.3 Recommender System 85 3.4 Interpreting Data Mining Results for Non-experts 85 4 Experimental Evaluation 88 4.1 Datasets Description 89 4.2 Classifiers Used in the Experiment 91 4.3 Generating the Knowledge Base 91 4.4 Results 91 5 Conclusions and Future Work 94 References 94 Combining Semantic Lifting and Ad-hoc Contextual Analysis in a Data Loss Scenario 97 1 Introduction and Problem Description 97 2 Related Work 100 3 KITE Methodology and RDF Graphs 102 3.1 RDF Graphs 104 4 KITE Metric System 106 4.1 Metric Definition Workflow 106 4.2 Knowledge Acquisition Process 107 5 Data Loss Case Study 111 5.1 The Data Loss Knowledge Acquisition Process 113 5.2 The Semantic Lifting 115 6 Conclusions 117 References 117 Comparative Process Mining in Education: An Approach Based on Process Cubes 120 1 Introduction 120 2 Process Mining 121 3 Process Cubes 123 4 Video Lectures: A Case Study 131 4.1 Data Available on Video Lectures and Exams 131 4.2 Identifying Events 132 4.3 Defining the Process Cube Structure and Selecting Views 132 4.4 Analyzing Process Cube Views: Some Examples 134 5 Requirements and Challenges 136 5.1 Performance 136 5.2 Interpreting the Results: Comparing Graphs 136 5.3 Refinements 137 6 Related Work 140 7 Conclusion 141 References 142 Author Index 145 This book constitutes the thoroughly refereed proceedings of the Second International Symposium on Data-Driven Process Discovery and Analysis held in Campione d'Italia, Italy, in June 2012. The six revised full papers were carefully selected from 17 submissions. To improve the quality of the contributions the symposium fostered the discussion during the presentation, giving authors the opportunity to improve their work extending the presented results. The selected papers cover topics spanning from theoretical issues related to process representation, discovery and analysis to practical and operational experiences in process discovery and analysis. Front Matter....Pages I-IX The Effect of Noise on Mined Declarative Constraints....Pages 1-24 Towards Collecting Sustainability Data in Supply Chains with Flexible Data Collection Processes....Pages 25-47 Handling Environment for Publicly Posted Composite Documents....Pages 48-64 Enabling Non-expert Users to Apply Data Mining for Bridging the Big Data Divide....Pages 65-86 Combining Semantic Lifting and Ad-hoc Contextual Analysis in a Data Loss Scenario....Pages 87-109 Comparative Process Mining in Education: An Approach Based on Process Cubes....Pages 110-134 Back Matter....Pages 135-135