Muutke küpsiste eelistusi

Smart Computing Applications in Crowdfunding [Kõva köide]

(Faculty of Engineering and the Built Environment, Institute for Intelligent Systems, University of Johannesburg), (Faculty of Engineering and the Built Environment, Department of Electrical and Electronic Engg. Science, University of J)
  • Formaat: Hardback, 532 pages, kõrgus x laius: 234x156 mm, kaal: 1043 g, 8 Illustrations, color; 54 Illustrations, black and white
  • Ilmumisaeg: 18-Dec-2018
  • Kirjastus: CRC Press
  • ISBN-10: 1138577715
  • ISBN-13: 9781138577718
Teised raamatud teemal:
Smart Computing Applications in CrowdfundingSuurem pilt
  • Formaat: Hardback, 532 pages, kõrgus x laius: 234x156 mm, kaal: 1043 g, 8 Illustrations, color; 54 Illustrations, black and white
  • Ilmumisaeg: 18-Dec-2018
  • Kirjastus: CRC Press
  • ISBN-10: 1138577715
  • ISBN-13: 9781138577718
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781138577718.html
Märksõnad:

This book focuses on smart computing for crowdfunding usage, looking at the crowdfunding landscape (e.g., reward-, donation-, equity-, P2P-based) and the crowdfunding ecosystem (e.g., regulator, asker, backer, investor, and operator). The increased complexity of fundraising scenario, driven by the broad economic environment as well as the need for using alternative funding sources, has sparked research smart computing techniques in this area. Covering a wide range of detailed topics, the authors of this book offer an outstanding overview of the current state of the art; providing deep insights into smart computing methods, tools, and their applications in crowdfunding; exploring the importance of smart analysis, prediction, and decision-making within fintech industry. This book is intended as an authoritative and valuable resource for professional practitioners and researchers alike, as well as financial, engineering, and computer science students who are interested in crowdfunding and other emerging fintech topics.

Foreword iii
Preface v
Acknowledgments v
List of Abbreviations
xvii
PART I Introduction
1(160)
1 Introduction to Smart Computing---Approximate Reasoning
3(54)
1.1 The Necessity of Computing in Practice: A Brief Reminder
3(16)
1.1.1 Practical Problems Generalization and Classification
4(1)
1.1.1.1 Learning the Current State of the World
5(1)
1.1.1.2 Predicting the Future State of the World
6(1)
1.1.1.3 Controlling the Desirable State of the World
6(1)
1.1.2 Computational Science and Engineering
7(1)
1.1.3 Key Concepts
8(1)
1.1.3.1 Sets
9(4)
1.1.3.2 Logic
13(1)
1.1.3.3 Probability Theory
14(2)
1.1.3.4 Possibility Theory
16(2)
1.1.3.5 Interval Analysis
18(1)
1.1.3.6 Category Theory
19(1)
1.2 The Unavoidability of Uncertainty in Reality: A Quick Retrospection
19(10)
1.2.1 Fuzziness
20(1)
1.2.2 Roughness
21(1)
1.2.3 Indefiniteness
22(1)
1.2.4 Relations Underlying the Uncertainties
23(1)
1.2.5 Measure Theory
24(1)
1.2.5.1 Entropy Measurement for Uncertainty---Shannon's Entropy for Classical System
24(3)
1.2.5.2 Entropy Measurement for Uncertainty---Fuzzy Entropy
27(1)
1.2.5.3 Entropy Measurement for Uncertainty---Rough Entropy
27(1)
1.2.5.4 Similarity Measurement for Uncertainty---General Similarity Measure
28(1)
1.2.5.5 Similarity Measurement for Uncertainty---Fuzzy Similarity Measure
28(1)
1.3 Smart Computing
29(2)
1.4 Data Analytics
31(6)
1.4.1 Define Critical Problem and Generate Working Plan
32(1)
1.4.2 Identify Data Sources
32(1)
1.4.3 Select and Explore the Data
32(2)
1.4.4 Clean the Data
34(1)
1.4.5 Transform, Segment, and Load the Data
34(1)
1.4.6 Model and Analyse the Data
35(2)
1.4.7 Interpretation, Evaluation and Deployment
37(1)
1.5 Conclusions
37(1)
References
38(19)
2 Introduction to Bricolage
57(20)
2.1 Innovation and Economy
57(4)
2.1.1 Innovation by Models
59(2)
2.1.2 Innovation by Types
61(1)
2.2 What is Bricolage?
61(3)
2.2.1 Bricolage Capabilities
62(1)
2.2.1.1 Build Something from Nothing
62(1)
2.2.1.2 Ability to Improvise
63(1)
2.2.1.3 Networking Ability
63(1)
2.2.2 Bricolage and Innovation
63(1)
2.2.2.1 New Angle of Service Innovation Thinking: Recombinative Thought (Bricolage-Based Viewpoint)
63(1)
2.3 Conclusions
64(2)
References
66(11)
3 Introduction to Service
77(26)
3.1 Service and Economy
77(12)
3.1.1 Factors of Production
78(1)
3.1.2 Goods vs. Services
78(1)
3.1.2.1 Tangible Goods
78(1)
3.1.2.2 Intangible Services
79(1)
3.1.2.3 Goods Sensitization
80(3)
3.1.3 Service Economy
83(2)
3.1.3.1 Computing-as-a-Service (CaaS)
85(3)
3.1.3.2 X-as-a-Service (XaaS)
88(1)
3.2 What is Service Science?
89(2)
3.2.1 Service Science: Newtonian Perspective
89(2)
3.2.2 Service Science: Systemic Perspective
91(1)
3.3 Service Innovation
91(5)
3.3.1 Types of Service Innovations
92(2)
3.3.2 Benefits of Servitization
94(2)
3.4 Conclusions
96(1)
References
96(7)
4 Introduction to Financial Service Innovation---Crowdfunding
103(58)
4.1 Financial Services
103(3)
4.1.1 Goods or Services
103(1)
4.1.1.1 Financial Services as Goods
104(1)
4.1.1.2 Financial Services as Services
104(1)
4.1.2 Problems and Challenges Faced by Traditional Financial Services
105(1)
4.2 Digital Transformation in Financial Services
106(12)
4.2.1 What is FinTech?
106(1)
4.2.2 The History of FinTech
107(1)
4.2.3 The Future of FinTech
108(1)
4.2.4 FinTech Ecosystem
109(1)
4.2.5 Disruptive FinTech Technologies
110(1)
4.2.5.1 Artificial Intelligence (AI)
111(1)
4.2.5.2 Internet of Things (IoT)
112(1)
4.2.5.3 Blockchain
112(1)
4.2.5.4 Big Data Analytics
113(1)
4.2.6 Landscape of FinTech Industry
114(1)
4.2.6.1 Financing
114(1)
4.2.6.2 Asset Management
115(1)
4.2.6.3 Payments
116(1)
4.2.6.4 Other FinTechs
117(1)
4.3 Crowdfunding
118(13)
4.3.1 What is Crowdfunding?
119(3)
4.3.2 The History of Crowdfunding
122(1)
4.3.3 Segments of Crowdfunding Platforms
123(1)
4.3.3.1 Reward-based Crowdfunding
124(1)
4.3.3.2 Donation-based Crowdfunding
125(1)
4.3.3.3 Peer-to-Peer-based Crowdfunding
125(1)
4.3.3.4 Equity-based Crowdfunding
126(2)
4.3.3.5 Mixed Crowdfunding
128(1)
4.3.4 Crowdfunding Ecosystem
129(1)
4.3.5 Crowdfunding User Manual
130(1)
4.4 Conclusions
131(1)
References
131(30)
PART II Regulator + Smart Computing = Healthier Market
161(52)
5 Crowdfunding Regulator---Technology Foresight and Type-2 Fuzzy Inference System
163(50)
5.1 Introduction
163(12)
5.1.1 Initial Coin Offering (ICO)
164(1)
5.1.2 Crypto Crowdfunding Platform: ICO Platform
165(1)
5.1.2.1 Blockchain 1.0: Decentralized Digital Ledger
165(1)
5.1.2.2 Blockchain 2.0: Smart Contract
166(1)
5.1.3 How does an ICO Work?
167(2)
5.1.4 Token Types and Characteristics
169(1)
5.1.5 The Similarities and Differences between General Crowdfunding and Crypto Crowdfunding
170(3)
5.1.6 A Brief Overview of Global ICO Regulatory Treatment
173(2)
5.2 Problem Statement
175(3)
5.2.1 Question 5.1
177(1)
5.3 Type-2 Fuzzy Sets for Question 5.1
178(17)
5.3.1 Type-2 Fuzzy Sets
178(1)
5.3.1.1 Basic Concept
179(1)
5.3.1.2 Operators
179(1)
5.3.1.3 Type-2 Fuzzy Inference System
180(5)
5.3.2 Technology Evolution via Interval Type-2 Fuzzy Inference System
185(1)
5.3.2.1 Framework Construction
185(4)
5.3.2.2 Summary
189(1)
5.3.3 Generic Technology Foresight Methods (TFM) Evaluation Procedure
190(1)
5.3.3.1 Phase 1---Qualitative Instance-Dependent Analysis
191(1)
5.3.3.2 Phase 2---Quantitative Instance- Independent Analysis
192(3)
5.3.3.3 Summary
195(1)
5.4 Conclusions
195(1)
References
196(17)
PART III Asker + Smart Computing = Better Feedback
213(50)
6 Crowdfunding Asker---Campaign Prediction and Ensemble Learning
215(48)
6.1 Introduction
215(10)
6.1.1 Determinants of Success and Failure: Reward-Based Crowdfunding Campaign
216(2)
6.1.2 Determinants of Success and Failure: Donation-Based Crowdfunding Campaign
218(2)
6.1.3 Determinants of Success and Failure: Peer-to-Peer (P2P)-Based Crowdfunding Campaign
220(4)
6.1.4 Determinants of Success and Failure: Equity-Based Crowdfunding Campaign
224(1)
6.2 Problem Statement
225(3)
6.2.1 Question 6.1
228(1)
6.3 Ensemble Learning for Question 6.1
228(19)
6.3.1 Boosting
234(1)
6.3.1.1 Forward Stepwise Additive Modelling
234(1)
6.3.1.2 Boosting Variants
235(3)
6.3.1.3 Why does Boosting Perform Better?
238(1)
6.3.2 Decision Trees
239(1)
6.3.2.1 Classification and Regression Trees (CART)
239(3)
6.3.2.2 Random Forests
242(1)
6.3.3 The Applications of Ensemble Learning in Predicting Project Success Rate and Fundraising Range
243(1)
6.3.3.1 Datasets
243(1)
6.3.3.2 Features
244(2)
6.3.3.3 Experimental Settings
246(1)
6.3.4 Summary
246(1)
6.4 Conclusions
247(1)
References
248(15)
PART IV Backer + Smart Computing = Firmer Support
263(52)
7 Crowdfunding Backer---Sentiment Analysis and Fuzzy Product Ontology
265(50)
7.1 Introduction
265(10)
7.1.1 Key Factors Influencing Backers' Donating Intention/Motivation in Non-Profit Campaigns
266(1)
7.1.2 Key Factors Influencing Backers' Donating Intention/Motivation in Incentive-Based Campaigns
267(2)
7.1.3 How to Pitch a Project?
269(1)
7.1.4 Sentiment Analysis
270(1)
7.1.4.1 The Role of Economic Sentiment
271(1)
7.1.4.2 Where can Sentiment Analysis Fit into Crowdfunding?
272(2)
7.1.4.3 Methods and Models for Sentiment Analysis
274(1)
7.2 Problem Statement
275(1)
7.2.1 Question 7.1
276(1)
7.3 Sentic Computing for Question 7.1
276(22)
7.3.1 Sentic Computing
276(1)
7.3.2 SenticNet
277(1)
7.3.2.1 Knowledge Acquisition
278(1)
7.3.2.2 Knowledge Representation
278(3)
7.3.2.3 Knowledge-Based Reasoning
281(4)
7.3.3 Fuzzy Product Ontology
285(1)
7.3.4 Latent Topic Modelling for Product Aspects Mining
285(1)
7.3.4.1 Notations
285(2)
7.3.4.2 Latent Dirichlet Allocation Topic Modelling
287(1)
7.3.4.3 LDA-Based Topic Modelling for Product Aspects Mining
288(3)
7.3.4.4 Context-Sensitive Sentiments Learning
291(2)
7.3.4.5 Aspect-Driven Sentiment Analysis
293(1)
7.3.4.6 Summary
294(1)
7.3.5 Analysis of Crowdfunding Project Videos
295(1)
7.3.5.1 Project Video Selection
296(1)
7.3.5.2 Video Watcher Survey
296(1)
7.3.5.3 Parameter Definition and Correlation Analysis
297(1)
7.3.5.4 Summary
298(1)
7.4 Conclusions
298(1)
References
299(16)
PART V Investor + Smart Computing = Fatter Return
315(44)
8 Crowdfunding Investor---Credit Scoring and Support Vector Machine
317(42)
8.1 Introduction
317(8)
8.1.1 Credit Risk in Online Peer-to-Peer (P2P) Lending
318(2)
8.1.2 Background of Credit Scoring
320(1)
8.1.3 Models and Mechanisms for Credit Scoring Analysis
321(1)
8.1.4 Multi-Dimensional Information for Credit Scoring Analysis
322(3)
8.2 Problem Statement
325(2)
8.2.1 Question 8.1
327(1)
8.3 Support Vector Machine for Question 8.1
327(17)
8.3.1 Support Vector Machine (SVM)
327(1)
8.3.1.1 Maximum Margin Hyperplane
328(2)
8.3.1.2 Lagrangian Methods for Constrained Optimization
330(2)
8.3.1.3 Kernel Functions
332(1)
8.3.1.4 Soft Margin Classifiers
333(3)
8.3.2 Fuzzy Support Vector Machine (FSVM)
336(1)
8.3.2.1 Standard Fuzzy Support Vector Machine (FSVM)
336(2)
8.3.2.2 Least Squares Fuzzy Support Vector Machine (FSVM)
338(2)
8.3.3 The Application of Support Vector Machine (SVM) in Credit Scoring
340(1)
8.3.3.1 Algorithm Implementation Environment Selection
340(1)
8.3.3.2 Data Description and Pre-Processing
340(2)
8.3.3.3 Feature Selection
342(1)
8.3.3.4 Model Selection
342(1)
8.3.3.5 Model Evaluation
343(1)
8.3.3.6 Experimental Study
343(1)
8.3.4 Summary
344(1)
8.4 Conclusions
344(2)
References
346(13)
PART VI Operator + Smart Computing = Wiser Service
359(88)
9 Crowdfunding Operator---Portfolio Selection and Metaheuristics
361(44)
9.1 Introduction
361(7)
9.1.1 The Role of Peer-to-Peer (P2P) Lending Platform Operator
362(5)
9.1.2 The Peer-to-Peer (P2P) Lending Mechanisms
367(1)
9.2 Problem Statement
368(3)
9.2.1 Question 9.1
370(1)
9.3 Metaheuristics for Question 9.1
371(20)
9.3.1 Search and Optimization---Hill Climbing
371(1)
9.3.2 Search and Optimization---Simulated Annealing
372(2)
9.3.2.1 Basic Simulated Annealing
374(1)
9.3.2.2 Cooling Scheme
374(1)
9.3.3 Search and Optimization---Genetic Algorithm
375(1)
9.3.3.1 Genetic Algorithm (GA) Framework
375(1)
9.3.3.2 Selection Strategy
376(2)
9.3.3.3 Mutation Strategy
378(1)
9.3.3.4 Crossover Strategy
378(1)
9.3.3.5 Replacement Strategy
379(1)
9.3.4 Search and Optimization---Particle Swarm Optimization
380(1)
9.3.4.1 Basic Particle Swarm Optimization (PSO)
380(1)
9.3.4.2 Neighbourhood Topology
381(1)
9.3.5 Portfolio Optimization in Stock Market Scenario
382(1)
9.3.5.1 Markowitz's Model
382(1)
9.3.5.2 Fuzzy Synthetic Evaluation and Genetic Algorithm (GA) for Portfolio Selection and Optimization
383(2)
9.3.5.3 Summary
385(1)
9.3.6 Loan Requests and Investment Offers Combination in Crowdfunding Scenario
386(1)
9.3.6.1 Problem Formulation
386(1)
9.3.6.2 Utility Functions
387(2)
9.3.6.3 Summary
389(2)
9.4 Conclusions
391(1)
References
392(13)
10 Crowdfunding Operator---Channel Competition, Strategic Interaction and Game Theory
405(42)
10.1 Introduction
405(3)
10.1.1 Successful Campaigns Using Generic Crowdfunding Channels
405(1)
10.1.2 Unsuccessful Campaigns Using Crowdfunding Channels
406(1)
10.1.3 Specialized Crowdfunding Channel Trials by Incumbents
407(1)
10.2 Problem Statement
408(2)
10.2.1 Question 10.1
409(1)
10.2.2 Question 10.2
409(1)
10.3 Game Theory for Question 10.1
410(9)
10.3.1 Experimental Setting
410(2)
10.3.1.1 Scenario 1: Producer and Service Supplier are Independent of Each Other
412(4)
10.3.1.2 Scenario 2: Producer and Service Supplier are Integrated
416(3)
10.3.2 Summary
419(1)
10.4 Quantum Games for Question 10.2
419(17)
10.4.1 Quantum Decision Theory
419(1)
10.4.1.1 Classical Utility Formulation
419(2)
10.4.1.2 States Space
421(1)
10.4.1.3 Mind and Entanglement
422(1)
10.4.1.4 Process of Decision-Making and the Strategic State
423(1)
10.4.2 Quantum Games and Quantum Strategies
424(1)
10.4.2.1 Classical EWL Model
424(5)
10.4.2.2 Generalized N Strategies
429(1)
10.4.2.3 Hamiltonian Strategic Interaction
430(2)
10.4.2.4 Ultimatum Game Illustration
432(4)
10.4.3 Summary
436(1)
10.5 Conclusions
436(1)
References
437(10)
PART VII Epilogue
447(10)
11 Outlook of Crowdfunding
449(8)
11.1 A Metaphor from the `Remembrance of Earth's Past' Trilogy
449(1)
11.2 Is Future Crowdfunding A `Dark Forest'?
449(1)
11.3 The Beginning of the End?
450(3)
11.3.1 N-Body Problem
450(1)
11.3.1.1 Newton's Laws and Two-Body Problem
451(1)
11.3.1.2 General Three-Body Problem
452(1)
11.4 Conclusions
453(1)
References
454(3)
Appendix A 457(46)
Index 503(6)
Prof. Ben's Bio-Sketch 509(2)
About the Authors 511
Bo Xing, D.Ing, is an Associate Professor at the Institute for Intelligent Systems, University of Johannesburg, South Africa. Prior to this, he was an Associate Professor at the Department of Computer Science, School of Mathematical and Computer Science, University of Limpopo, South Africa. He was a scientific researcher at the Council for Scientific and Industrial Research (CSIR), South Africa. He has published 3 books, over 50 research papers in the form of international journals, and international conference proceedings. His current research interests lie in applying various nature-inspired computational intelligence methodologies towards big data analysis, miniature robot design and analysis, advanced mechatronics system, and e-maintenance.



Tshilidzi Marwala, Ph.D, is the Vice Chancellor & Principal of the University of Johannesburg. He was previously the Deputy Vice Chancellor for Research and Internationalisation as well as the Dean of Engineering at the University of Johannesburg. He was a full Professor of Electrical Engineering, the Carl and Emily Fuchs Chair of Systems and Control Engineering as well as the SARChI Chair of Systems Engineering at the University of the Witwatersrand. He was also an executive assistant to the technical director at the South African Breweries. He has published 12 books (one has been translated into Chinese), over 280 papers in journals, proceedings, book chapters and magazines and holds three international patents. His research interests are multi-disciplinary, and they include the theory and application of computational intelligence to engineering, computer science, finance, social science and medicine.