Applications of Emerging Technologies and AI/ML Algorithms: International Conference on Data Analytics in Public Procurement and Supply Chain (ICDAPS2022)

Description

This book provides practical insights into applications of the state-of-the-art of Machine Learning and Artificial Intelligence (AI) for solving intriguing and complex problems in procurement and supply chain management. The application domain includes perishable food supply chain, steel price prediction, electric vehicle charging infrastructure design, contract price negotiation, reverse logistics network design, and demand forecasting. Further, the book highlights the advanced topics in the procurement field, like AI in green procurement and e-procurement in the pharma sector. Furthermore, the book covers applications of well-established methodologies such as heuristics, optimization, game theory, and MCDM based on the nature of the problem. The inclusion of the vaccine supply chain digital twin and blockchain-based procurement signals the significance of the book. This book is a comprehensive guide for industry professionals to understand the power of data analytics, enabling them to improve efficiency and effectiveness in the procurement and supply chain sectors. Foreword Contents About the Editors 1 Q-learning Approach to Mitigate Bacterial Contamination in Food Supply Chain 1.1 Introduction 1.2 Traceability in Supply Chain Data—Blockchain Technology 1.3 Monitoring Parameters and Optimization: Q-learning Model 1.4 Experiments and Analysis 1.5 Conclusion References 2 Optimization of Network Planning in a Real-Life Vehicle Logistics Distribution System 2.1 Introduction 2.2 Problem Description 2.3 Related Research 2.4 Methodology 2.5 Results 2.6 Conclusions References 3 Efficient Supplier Selection in e-Procurement Using Graph-Based Model 3.1 Introduction 3.2 Problem Description 3.3 Methodology 3.3.1 Data Collection 3.4 Results and Analysis 3.5 Conclusion References 4 Understanding the Role of e-Procurement and Blockchains in Government Tendering—A Case Evidence from China 4.1 Introduction 4.1.1 Challenges of Chinese Government Open Tendering 4.1.2 Blockchain and e-Procurement in Government Tendering 4.2 Methodology 4.3 Findings and Discussions 4.4 Conclusions References 5 Omni-Channel Distribution Network Design for Fresh Food Procurement Considering Freshness-Keeping Effort and Food Quality Loss 5.1 Introduction and State of the Art 5.2 Problem Description and Formulation 5.3 Numerical Study and Analysis 5.4 Conclusions References 6 Redesigning of Procurement Distribution System Network: An Application of Clustering Algorithms 6.1 Introduction 6.2 Literature Review 6.3 Model Formulation 6.4 Solution Methodology 6.5 Results and Discussions 6.6 Conclusions References 7 Big Data Analytics and Its Applications in Supply Chain Management: A Literature Review Using SCOR Model 7.1 Introduction 7.2 Research Methodology 7.3 Descriptive Analysis 7.3.1 Year Wise Publications 7.3.2 Methodological Distribution of Articles 7.3.3 Distribution of BDA Types 7.3.4 Distribution of BDA Tools 7.4 Thematic Analysis 7.4.1 Plan Process 7.4.2 Source Process 7.4.3 Make Process 7.4.4 Deliver Process 7.4.5 Return Process 7.5 Conclusion and Future Work References 8 Leveraging Machine Learning of Indian Railways Public Procurement Data for Managerial Insights 8.1 Introduction 8.2 Literature Survey 8.3 Model Development 8.3.1 Feature Selection and Data Preparation 8.3.2 Model Building 8.4 Model Results 8.4.1 Influential Features for Performance Parameters 8.4.2 Comparative Performance Analysis of Administrative Zones 8.5 Conclusion References 9 Blockchain Technology and Its Application in 3D Parts Procurement: A Case Study 9.1 Introduction 9.2 Literature Review of Blockchain with Application in Supply Chain 9.3 Additive Manufacturing & Blockchain-Based AM Decentralized Supply Networks 9.4 Scheduling 3D Printers 9.4.1 Mathematical Model 9.5 A Case Study and Results 9.6 Conclusions References 10 A Mathematical Model-Based Heuristic for Clustering, Logistics, and Order Pickup in the Constrained In-Bound Multi-Period Multi-Part Inventory Routing Problem with Heterogeneous Vehicles 10.1 Introduction 10.1.1 Inventory Routing Problem 10.2 Literature Review 10.2.1 Literature Review on Multi-Product Multi-Period IRP 10.2.2 Complexity of IRP 10.2.3 Research Gaps Identified from the Literature Review 10.3 Proposed Methodology for CIBIRPHV 10.3.1 An Introduction to the Problem Statement 10.3.2 The Proposed Methodology 10.4 Computational Results 10.5 Conclusion and Future Work References 11 Performance Evaluation of Trucking Industry Using BSC and DEA: A Truck Driver’s Perspective 11.1 Introduction 11.2 Literature Review 11.3 Methodology 11.4 Results and Discussions 11.5 Conclusion References 12 E-procurement: An Emerging Tool for Pharmaceutical Supply Chain Management 12.1 Introduction 12.2 Literature Review 12.3 Methodology 12.3.1 Data Collection and Analysis 12.4 Results and Discussions 12.5 Limitations, Future Scope and Conclusion References 13 Risk and Feasibility of Sustainable Techno-Eco-Env Green Supply Chain 13.1 Introduction 13.2 Model 13.3 Methodology 13.4 Data Collection 13.5 Results and Discussions 13.5.1 Site Location and Connectivity 13.5.2 Cost Analysis and GHGe 13.5.3 Threshold Value of NPV 13.6 Conclusion Appendix A—Nomenclature References 14 Steel Price Forecasting for Better Procurement Decisions: Comparing Tree-Based Decision Learning Methods 14.1 Introduction and Background 14.2 Methodology 14.2.1 Regression Trees 14.2.2 Random Forest 14.3 Data Description and Empirical Results 14.3.1 Variable Selection and Data Collection 14.3.2 Correlation Between Steel Price and Selected Variables 14.3.3 Framework and Results 14.4 Conclusions References 15 An Interactive Game Theory Analytics to Model the Panic Buying When the Downstream Supply Chain Channel Partners Undergo Horizontal Coopetition 15.1 Introduction 15.2 Literature Review 15.3 Interactive Analytics and Models 15.4 Propositions 15.5 Discussions 15.6 Conclusions References 16 Supply Chain Data Analytics for Predicting Delivery Risks Using Machine Learning 16.1 Introduction 16.2 Literature Review 16.3 Methodology 16.3.1 Dataset 16.3.2 Exploratory Data Analysis and Pre-processing 16.3.3 Feature Engineering 16.3.4 Selection of Suitable Performance Metrics 16.3.5 Algorithm and Feature Selection 16.4 Results and Discussions 16.4.1 Results Comparison and Evaluation 16.4.2 K-fold cross-validation 16.5 Conclusion 16.5.1 Conclusion 16.5.2 Future Research Avenues References 17 Importance of Equitable Public Procurement of Food Grains in India for Sustainability 17.1 Introduction 17.2 Methodology 17.3 Results 17.4 Conclusion References 18 A Framework for 5G Enabled Vaccine Supply Chain Digital Twin 18.1 Introduction 18.2 5G Enabled Vaccine Supply Chain Framework: Digital Twin 18.2.1 Timely Response 18.2.2 Improved Visibility 18.2.3 Improved Connectivity 18.3 Expected Response of Proposed Framework 18.4 Application of 5G Technologies on Vaccine Supply Chain 18.4.1 Strategic Level 18.4.2 Operational Level 18.4.3 Cross-Functional Level 18.5 Discussion 18.6 Conclusion and Future Scope References 19 Issues in Procurement and Distribution of Plantation Crops: Can AI-ML Technologies Offer Better Performance Outcomes? 19.1 Introduction 19.2 Plantation Crops, Procurement Process, and Related Issues 19.2.1 The Procurement and Distribution Process 19.2.2 Case Study: Procurement and Distribution Issues in Rubber Value Chain 19.3 Comparing Current Business Practices with Data Analytics and AI-ML Enabled Outcomes 19.4 Discussion References 20 Quantifying the Quality Grade of the Return Mobile Phone in the Context of a Retail Store 20.1 Introduction 20.2 Research Methodology 20.2.1 Determination of Closeness Ratio Using TOPSIS 20.2.2 Determination of Composite Reduction Index (CRI) for Cell Phone Quality Evaluation 20.2.3 Data Creation and Cleaning 20.3 Result and Discussion 20.3.1 Survey Data Analysis 20.3.2 Ranking of Influencing Factors by TOPSIS and Their Correlation 20.3.3 Composite Reduction Index for Return Smartphone 20.4 Conclusion References 21 Integrated Blockchain Architecture for End-to-End Receivables Management of Indian MSMEs 21.1 Introduction 21.2 Literature Review 21.3 Government Initiatives and Current Challenges 21.3.1 Problems with MSME SAMADHAAN 21.3.2 Problems with TReDS 21.4 Blockchain-Based MSME Receivables Management Platform 21.4.1 Platform and Methodology 21.4.2 System Design 21.5 Conclusion References 22 Investigating the Key Enablers in Perishable Food Supply Chain Using DEMATEL and AHP—PROMETHEE 22.1 Introduction 22.2 Related Work 22.2.1 Enablers Related to PFSC 22.2.2 DEMATEL and AHP—PROMETHEE II Approaches 22.2.3 Summary 22.3 Methodology 22.3.1 Dematel 22.3.2 Dematel 22.3.3 Integrated AHP-PROMETHEE II 22.3.4 Promethee Ii 22.4 Findings and Discussions 22.5 Conclusions References 23 Blockchain for Supply Chain for Perishable Goods 23.1 Introduction 23.2 Literature Review 23.3 Problem Description 23.4 Solution Approach 23.5 Results and Discussion 23.6 Conclusion References 24 A Novel Linear Mathematical Model Based Heuristic for a Class of Classification Problem with Non-linearly Separable Data 24.1 Introduction 24.2 Literature Review 24.3 The Proposed Binary Classification Model 24.3.1 The Iris Dataset 24.3.2 The Linear Programming Model for Binary Classification 24.4 Numerical Illustration and Results 24.4.1 Accuracy of the Proposed Heuristic 24.5 Conclusion and Future Work References 25 Intermittent Demand Forecasting for Handtools in Forging Industries: A Svm Model 25.1 Introduction 25.2 Demand Estimation Methods 25.2.1 Support Vector Regression (SVR) 25.2.2 Adaptive Univariate Svm (Support Vector Machine) Regression 25.3 Experimental Setting 25.3.1 Datasets 25.3.2 Performance Criteria 25.3.3 Experimental Results 25.4 Conclusions References 26 Electric Vehicle and Charging Infrastructure Development: A Comprehensives Review Using Science Mapping and Thematic Analysis 26.1 Introduction 26.2 Review Methodology 26.2.1 Phase I: Bibliometric Search 26.2.2 Phase II: Descriptive Analysis 26.2.3 Phase III: Scientometric Analysis 26.2.4 Phase IV: Citation Network Analysis 26.3 Results & Discussion 26.3.1 Descriptive Analysis 26.3.2 Scientometric Analysis 26.3.3 Citation Network Analysis/Thematic Analysis 26.4 Discussion 26.5 Conclusion References 27 Contract Price Negotiation Using an AI-Based Chatbot 27.1 Introduction 27.1.1 Contract Management Process 27.1.2 AI-Based Chatbot 27.1.3 Negotiation Process 27.2 Literature Survey 27.2.1 Impact of AI in Procurement Using a Chatbot 27.2.2 ML-Based Price Negotiation 27.2.3 Natural Language Processing: An Interactive Chatbot 27.3 Methodology 27.3.1 Recommended Cost Determination 27.3.2 Decision Bot 27.3.3 Interface of Negotiating Bot 27.4 Conclusions and Future Work References 28 A Deep Learning-Based Reverse Logistics Model for Recycling Construction and Demolition Waste 28.1 Introduction 28.2 Related Work 28.3 Method and Models 28.3.1 Dataset 28.3.2 Pre-processing 28.3.3 Proposed an End-to-End Improved Convolutional Neural Network (EEI-CNN) Based Reverse Logistics Model for Recycling Construction and Demolition Waste 28.4 Evaluation Metrics 28.5 Result and Discussion 28.6 Conclusion References 29 Supplier Prioritization and Risk Management in Procurement 29.1 Introduction 29.2 Literature Review 29.3 Overview of Supplier Prioritization 29.3.1 Supplier Prioritization Criteria 29.4 Overview of Risk Management in Procurement 29.4.1 Risk Management in Procurement 29.4.2 Risk Management Approaches in Procurement 29.5 Opportunities and Challenges 29.6 Conclusions References 30 Development of an Integrated Customer Relationship Management Tool for Predictive Analytics in Supply Chain Management 30.1 Introduction 30.2 Literature Review 30.2.1 CRM: Customer Relationship Management 30.2.2 Supply Chain Management: Integration with CRM 30.2.3 Customer Segmentation and Classification: Grouping of Customers 30.2.4 Product Recommendation: Efficient Promotion of Products 30.2.5 Customer Linked Prediction 30.3 Decision-Making Framework 30.3.1 Model Overview 30.3.2 Data Preparation 30.3.3 Customer Segmentation and Classification 30.3.4 Product Recommendation 30.3.5 Customer Linked Predictions 30.3.6 Sales Forecasting 30.3.7 Web Application Overview 30.4 Experimental Analysis and Results 30.4.1 A Case Study 30.4.2 Feature Engineering Analysis and Results 30.4.3 Customer Segmentation and Classification Results 30.4.4 Sales Forecasting Results 30.5 Conclusion 30.5.1 Research Contributions 30.5.2 Potential Future Research References 31 Predicting Top Companies Amid Changing Macro Environment—Optimal Sampling Imposing Restriction Filters 31.1 Introduction 31.1.1 Predicting Top Companies to Win Market 31.1.2 Machine Learning in Predicting Top Companies 31.1.3 Constrained Sample in Financial Health Prognosis 31.2 Restriction Filters for Datasets 31.2.1 Filter on Industry 31.2.2 Filter on Capitalization 31.2.3 Filter on Completeness 31.2.4 Filter on Multiple Constraints 31.2.5 Filter on History 31.3 Restriction Filters for Training Sets 31.3.1 Filter on Performance 31.3.2 Filter on Environment 31.4 Moving Window System 31.4.1 Training and Testing Window 31.4.2 Top Companies Selection Window: Cases and Scenarios 31.4.3 Training Window Optimization 31.4.4 Testing Window Optimization 31.4.5 Advantages of the Moving Window System 31.5 Conclusions 31.6 Limitations and Challenges 31.7 Scope for Further Studies References 32 Role of Artificial Intelligence in Green Public Procurement 32.1 Introduction 32.1.1 Green Public Procurement 32.1.2 AI and Green Public Procurement 32.2 Application of AI in Green Public Procurement 32.2.1 Regulatory Technology 32.2.2 Pollution 32.2.3 Energy 32.2.4 Water Management 32.2.5 Climate Change 32.2.6 Biodiversity and Ecology 32.2.7 Material Resources 32.3 Findings and Suggestions 32.3.1 Findings 32.3.2 Suggestions References 33 Supplier Prioritization and Risk Management in Procurement 33.1 Introduction 33.2 Literature Review 33.3 Supplier Management 33.4 Supplier Prioritization 33.5 Risk Management 33.5.1 Live Case 33.6 Conclusion References 34 An Empirical Study on Recruitment Management Systems: Start of a New Era 34.1 Introduction 34.2 Review of Literature 34.3 Objectives of the Study 34.4 Sample Design and Methodology 34.4.1 Method of Research 34.4.2 Sampling Technique 34.4.3 Sample Unit 34.4.4 Sample Size 34.5 Limitations of Study 34.6 Data Analysis 34.6.1 Social Recruiting: (SR) 34.6.2 Programmatic Job Advertisements: (PJA) 34.6.3 Application Tracking System: (ATS) 34.7 Findings 34.8 Conclusion References 35 Traceability of Unwitting Disclosure Using Explainable Correlation in Procurement and Supply Chain 35.1 Purpose of Research 35.2 Methodology 35.3 Example 35.4 Implications 35.5 Conclusion References