Agent-Mediated Electronic Commerce and Trading Agent Design and Analysis (eBook)

AAMAS Workshop, AMEC 2008, Estoril, Portugal, May 12-16, 2008, and AAAI Workshop, TADA 2008, Chicago, IL, USA, July 14, 208, Revised, Selected Papers

Wolfgang Ketter, Han Poutré, Norman Sadeh, Onn Shehory, William Walsh (Autoren)

eBook Download: PDF

2010 | 1. Auflage
201 Seiten
Springer-Verlag
978-3-642-15237-5 (ISBN)

Infos

This volume contains 13 thoroughly refereed and revised papers detailing recent advances in research on trading agents, negotiating agents, dynamic pricing, and auctions. They were originally presented at the 10th International Workshop on Agent-Mediated Electronic Commerce (AMEC 2008) collocated with AAMAS 2008 in Estoril, Portugal, or the 6th Workshop on Trading Agent Design and Analysis (TADA 2008) collocated with AAAI 2008 in Chicago, IL, USA. The papers originating from AMEC 2008 address agent modeling and multi-agent problems in the context of e-negotiations and e-commerce. The TADA papers stem from the effort to design scenarios where trading agents and market designers can be pitched against each other in applications from supply chain management and procurement. They are all characterized by interdisciplinary research combining fields such as artificial intelligence, distributed systems, game theory, and economics.

Inhalt

Preface 5
Organization 8
Table of Contents 10
Preventing Under-Reporting in Social Task Allocation 12
Introduction 12
Preliminaries 13
An Exact VCG Mechanism for STAP 16
A Greedy Mechanism for STAP 19
A Greedy Allocation Algorithm 19
A Mechanism That Is Truthful with Respect to Under-Reporting 21
Experiments 22
Discussion and Conclusions 24
References 25
Reasoning and Negotiating with Complex Preferences Using CP-Nets 26
Introduction 26
Representing and Ordering Preferences 27
Ceteris Paribus Nets (CP-Nets) 28
Obtaining Preferences 30
Strategies for Generating Requests 31
Sequential Search Strategy 32
Depth Limited Search Strategy 32
Binary Search Strategy 33
Upper Random Strategy 34
Producer’s Strategy for Counter Offer 35
Experiments 35
Discussion 38
References 39
Using Priced Options to Solve the Exposure Problem in Sequential Auctions 40
Introduction 40
Options: Basic Definition 41
RelatedWork 41
Outline and Contribution of Our Approach 42
Expected Profit for a Sequence of n Auctions and 1 Synergy Bidder 42
Profit with n Unique Goods without Options 42
Profit with n Unique Goods with Options 44
When Options Can Benefit Both Synergy Bidder and Seller 45
The Case When Agents Are Better Off with Options 45
Synergy Bidder’s Profit-Maximizing Bid 49
Simulation of a Market with a Single Synergy Bidder 50
Synergy Bidder’s Strategy 51
Experimental Results: Market Entry Effect for One Synergy Bidder 51
Multiple Synergy Bidders 52
Two Synergy Bidders Interacting Indirectly through the Exercise Price Level 53
Direct Synergy Bidder Competition in the Same Auctions 53
Larger Simulation with Random Synergy Bidders’ Market Entry 54
Discussion and Further Work 55
References 55
Towards a Quality Assessment Method for Learning Preference Profiles in Negotiation 57
Introduction 57
Related Work and Problem Description 58
Quality Assessment Method 60
Quality Measures 60
Negotiation Domains and Profiles 62
Negotiation Strategies of the Opponent 64
Application and Experimental Results 65
Experimental Setup 65
Evaluation 66
Conclusion and Discussion 68
References 69
Using a Memory Test to Limit a User to One Account 71
Introduction 71
TestSpecifics 74
A Small Study with Human Subjects 75
A Game-Theoretic Analysis 77
Conclusions and Future Research 79
References 81
Appendix: Another Test Based on Recognizing Faces 82
Multi-attribute Regret-Based Dynamic Pricing 84
Introduction 84
Dynamic Pricing over Multiple Product Attributes 85
Minimax Regret-Based Algorithms 87
Minimax Regret-Based Attribute Prediction 88
Regret-Based Dynamic Pricing 90
Simulation Results 91
Comparison Strategies 91
Experimental Results 93
Related Work 96
Conclusion 97
References 97
On the Economic Effects of Competition between Double Auction Markets 99
Introduction 99
Background 100
Experimental Setup 101
Software 101
Traders 102
Markets 103
Experiments 103
Measurements 104
Results 105
Discussion 107
Conclusions 111
References 112
A Multiagent Recommender System withTask-Based Agent Specialization 114
Introduction 114
Related Work 116
Recommender Systems 116
Multiagent Recommender Systems 117
MAS Recommendation Model 118
The Agents 118
The Recommendation Algorithm 121
Experimental Results 122
Conclusions 126
References 127
Towards Automated Bargaining in Electronic Markets: A Partially Two-Sided Competition Model 128
Introduction 128
Alternating-Offers Bargaining with Agents’ Deadlines 129
The Proposed Model 133
Equilibrium Strategies 135
Base Case: One Buyer and One Seller 135
One-Sided Competition I: One Buyer and More Sellers 137
One-Sided Competition II: More Buyers and One Seller 138
Two-Sided Competition: More Buyers and More Sellers 138
Conclusions and Future Works 140
References 141
Bidding Heuristics for Simultaneous Auctions:Lessons from TAC Travel 142
Introduction 142
TACTravelGame 143
Bidding Heuristics 143
Marginal-Utility-Based Heuristics 144
Sample Average Approximation 145
Experiments in TAC Travel-Like Auctions 146
Decision-Theoretic Experiments with Perfect Distributional Prediction 147
Setup 148
Results 148
Decision-Theoretic Experiments with Imperfect Distributional Prediction 149
Setup 149
Results 150
Experiments with Competitive Equilibrium Prices 152
Setup 152
Decision-Theoretic Experiments 152
Game-Theoretic Experiments 153
Summary and Discussion of Experimental Results 154
Related Work 154
Conclusion 155
References 156
Applications of Classifying Bidding Strategies for the CAT Tournament 158
Introduction 158
Bidding Strategies 159
Classifying Traders by Bidding Strategies 160
Data Collection 160
Classification Using a Support Vector Machine 161
Classification Using a Hidden Markov Model 162
Alternative Classification Techniques 163
Utilizing Classification to Determine Optimal Action Policies 164
Experimental Results 165
Testing Environment 165
Fee Adjustments 166
Experiments 166
Determining Optimal Actions Using an MDP 169
Conclusion and Future Work 169
References 170
Coordinating Decisions in a Supply-Chain Trading Agent 172
Introduction 172
Overview of the TAC SCMGame 173
Agent Decision Processes 174
Game Balance 175
Agent Design and the Decision Coordination Problem 176
Predicted Sales Volume 177
Future Production Schedule 178
InventoryManagement 179
Central StrategyModule 181
Separate Supply and Demand Models 182
Internal Markets 182
Conclusions and Future Work 183
References 184
The 2007 TAC SCM Prediction Challenge 186
Introduction 186
The Prediction Challenge 186
Prediction Methods 189
Results and Analysis 192
Results 192
Average Daily Errors 192
Differences between Participants across Games 195
Differences between Participants across Days 198
Conclusion 199
References 200
Author Index 201

Produkt-Details

• Erscheint lt. Verlag: 1.1.2010
• Sprache: englisch
• Themenwelt: Mathematik / Informatik ► Informatik ► Datenbanken
• Themenwelt: Informatik ► Office Programme ► Outlook
• Themenwelt: Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
• Themenwelt: Mathematik / Informatik ► Mathematik ► Finanz- / Wirtschaftsmathematik
• Themenwelt: Sozialwissenschaften ► Politik / Verwaltung ► Staat / Verwaltung
• ISBN-10: 3-642-15237-6 / 3642152376
• ISBN-13: 978-3-642-15237-5 / 9783642152375