Skip to main content

A Machine Learning Approach for Mechanism Selection in Complex Negotiations

Abstract

Automated negotiation mechanisms can be helpful in contexts where users want to reach mutually satisfactory agreements about issues of shared interest, especially for complex problems with many interdependent issues. A variety of automated negotiation mechanisms have been proposed in the literature. The effectiveness of those mechanisms, however, may depend on the characteristics of the underlying negotiation problem (e.g. on the complexity of participant’s utility functions, as well as the degree of conflict between participants). While one mechanism may be a good choice for a negotiation problem, it may be a poor choice for another. In this paper, we pursue the problem of selecting the most effective negotiation mechanism given a particular problem by (1) defining a set of scenario metrics to capture the relevant features of negotiation problems, (2) evaluating the performance of a range of negotiation mechanisms on a diverse test suite of negotiation scenarios, (3) applying machine learning techniques to identify which mechanisms work best with which scenarios, and (4) demonstrating that using these classification rules for mechanism selection enables significantly better negotiation performance than any single mechanism alone.

This is a preview of subscription content, access via your institution.

References

  1. Aydoğan, R., Festen, D., Hindriks, K. & Jonker, C. M. (2017). Alternating offers protocol for multilateral negotiation. In K. Fujita, Q. Bai, T. Ito, M. Zhang, F. Ren, R. Aydoğan, & R. Hadfi (eds), Modern Approaches to Agent-based Complex Automated Negotiation, pp. 153–167, Springer.

  2. Alpaydin, E. (2009). Introduction to Machine Learning. MIT Press.

    MATH  Google Scholar 

  3. Aydoğan, R., Hindriks, K. & Jonker, C. (2014). Multilateral mediated negotiation protocols with feedback. In I. Marsa-Maestre, M. A. Lopez-Carmona, T. Ito, M. Zhang, Q. Bai, & K. Fujita (eds), Novel Insights in Agent based Complex Automated Negotiation, Studies in Computational Intelligence, pp. 43–59, Springer.

  4. Bai, Q., Zhang, M. & Sim, K. M. (2009). Flexible negotiation modelling by using coloured Petri Nets. Journal of Information Technology Research, 2(3): 1–17.

    Article  Google Scholar 

  5. Chen, S., Ammar, H., Tuyls, K. & Weiss, G. (2012). Transfer learning for bilateral multi-issue negotiation, In Proceedings of the 24th Benelux Conference on Artificial Intelligence (BNAIC), pp. 59–66, 2012.

    Google Scholar 

  6. Endriss, U. (2006). Monotonic concession protocols for multilateral negotiation, In Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 392–399, Japan, 2006.

    Chapter  Google Scholar 

  7. Fujita, K., Ito, T., & Klein, M. (2012). A secure and fair protocol that addresses weaknesses of the Nash bargaining solution in nonlinear negotiation. Group Decision and Negotiation, 21(1): 29–47.

    Article  Google Scholar 

  8. Guerri, A. & Milano, M. (2004). Learning techniques for automatic algorithm portfolio selection, In Proceedings of the 16th European Conference on Artificial Intelligence, pp. 475–479, 2004.

    Google Scholar 

  9. Ilany, L. & Gal, Y. (2016). Algorithm selection in bilateral negotiation. Autonomous Agents and Multi-Agent Systems, 30(4): 697–723.

    Article  Google Scholar 

  10. Ito, T. & Klein, M. (2009). A consensus optimization mechanism among agents based on genetic algorithm for multi-issue negotiation problems, In Proceedings of Joint Agent Workshops and Symposium (JAWS), pp. 286–293, 2009.

    Google Scholar 

  11. Ito, T., Hattori, H. & Klein, M. (2007). Multi-issue negotiation protocol for agents: exploring nonlinear utility spaces. In Proceedings of International Joint Conference on Artificial Intelligence, pp. 1347–1352, 2007.

    Google Scholar 

  12. Jennings, N., Faratin, P., Lomuscio, A., Parsons, S., Sierra, C., & Wooldridge, M. (2001). Automated negotiation: prospects, methods and challenges. International Journal of Group Decision and Negotiation, 10(2): 199–215.

    Article  Google Scholar 

  13. Jonge, D. d. & Sierra, C. (2015). Nb3: A multilateral negotiation algorithm for large, nonlinear agreement spaces with limited time. Autonomous Agents and Multi-Agent Systems, 29(5): 896–942.

    Article  Google Scholar 

  14. Jonker, C. M., Aydogan, R., Baarslag, T., Fujita, K., Ito, T. & Hindiks, K. (2017). Automated Negotiating Agents Competition (ANAC), In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17), pp. 5070–5072, 2017.

    Google Scholar 

  15. K., V. V., Fogarty, T. C. & Miller, J. F. (2003). Smoothness, ruggedness and neutrality of fitness landscapes: from theory to application. In Advances in Evolutionary Computing: 3–44, Springer.

    Google Scholar 

  16. Kersten, G. E. & Lai, H. (2007). Negotiation support and e-negotiation systems: an overview. Group Decision and Negotiation, 16(6): 553–586.

    Article  Google Scholar 

  17. Klein, M., Faratin, P., Sayama, H. & Bar-Yam, Y. (2003). Protocols for negotiating complex contracts. IEEE Intelligent Systems, 18: 32–38.

    MATH  Article  Google Scholar 

  18. Kraus, S. (2001). Strategic Negotiation in Multi-Agent Environments. Cambridge. The MIT Press.

    MATH  Google Scholar 

  19. Lai, G. & Sycara, K. (2009). A generic framework for automated multi-attribute negotiation. International Journal of Group Decision and Negotiation, 18(2): 169–187.

    Article  Google Scholar 

  20. Lang, F. & Fink, A. (2015). Learning from the metaheuristics: protocols for automated negotiations. Group Decision and Negotiation, 24(2): 299–332.

    Article  Google Scholar 

  21. Leo Breiman, J. F. (1984). Classification and Regression Trees. Taylor & Francis.

    MATH  Google Scholar 

  22. Leyton-Brown, K., Nudelman, E. & Shoham, Y. (2002). Learning the empirical hardness of optimization problems: The case of combinatorial auctions. International Conference on Principles and Practice of Constraint Programming: 556–572, Springer.

    Google Scholar 

  23. Leyton-Brown, K., Nudelman, E., Andrew, G., McFadden, J. & Shoham, Y. (2003). A portfolio approach to algorithm select, In Proceedings of the 18th International Joint Conference on Artificial intelligence, pp. 1542–1543. Morgan Kaufmann Publishers Inc.

    Google Scholar 

  24. Lin, R. (2004). Bilateral multi-issue contract negotiation for task redistribtion using a mediation service, In Proceedings of Agent Mediated Electronic Commerce VI.

    Google Scholar 

  25. Lin, R., Kraus, S., Baarslag, T., Tykhonov, D., Hindriks, K. & Jonker, C. M. (2014). Genius: An integrated environment for supporting the design of generic automated negotiators. Computational Intelligence, 30(1): 48–70.

    MathSciNet  Article  Google Scholar 

  26. Marsa-Maestre, I., Klein, M., de la Hoz, E. & Lopez-Carmona, M. A. (2011). Negowiki: A set of community tools for the consistent comparison of negotiation approaches, In Proceedings of International Conference on Principles and Practice of Multi-Agent Systems 2011: 424–435, Springer.

    Google Scholar 

  27. Marsa-Maestre, I., Klein, M., Jonker, C. M.& Aydogan, R. (2014). From problems to protocols: towards a negotiation handbook. Decision Support Systems, 60(1):39–54.

    Article  Google Scholar 

  28. Marsa-Maestre, I., Lopez-Carmona, M. A., Klein, M., Ito, T. & Fujita, K. (2012). Addressing utility space complexity in negotiations involving highly-uncorrelated, constraint-based utility spaces. Computational Intelligence, 30(1):1–29.

    MathSciNet  Article  Google Scholar 

  29. Peyman, F., Sierra, C. & Jennings, N. R. (1998). Negotiation decision functions for autonomous agents. Robotics and Autonomous Systems, 24(3): 159–182.

    Google Scholar 

  30. Ren, F., & Zhang, M. (2014). A single issue negotiation model for agents bargaining in dynamic electronic markets. Decision Support Systems, 60: 55–67.

    Article  Google Scholar 

  31. Rubinstein, A. (1982). Perfect equilibrium in a bargaining model. Econometrica, 50(1): 97–109.

    MathSciNet  MATH  Article  Google Scholar 

  32. Sanchez-Anguix, V., Aydoğan, R., Julian, V., Garcia-Fornes, A. & Jonker, C. M. (2014). Unanimously acceptable agreements for negotiation teams in unpredictable domains. Electronic Commerce Research and Applications, 13(4): 243–265.

    Article  Google Scholar 

  33. Tomassini, M., Vanneschi, L., Collard, P. & Clergue, M. (2005). A study of fitness distance correlation as a difficulty measure in genetic programming. Evolutionary Computation, 13(2): 213–239.

    MATH  Article  Google Scholar 

  34. Williams, C. R. R. V., Gerding, E. H. & Jennings, N. R. (2012). Negotiating concurrently with unknown opponents in complex, real-time domains. Proceedings of 20th European Conference on Artificial Intelligence: 834–839.

    Google Scholar 

  35. Williams, C. R., Robu, V., Gerding, E. H. & Jennings, N. R. (2011). Using gaussian processes to optimise concession in complex negotiations against unknown opponents, In Proceedings of the 22nd International Joint Conference on Artificial Intelligence, pp. 432–438, AAAI Press.

    Google Scholar 

  36. Wong, T. & Fang, F. (2010). A multi-agent protocol for multilateral negotiations in supply chain management. International Journal of Production Research, 48(1): 271–299.

    MATH  Article  Google Scholar 

Download references

Acknowledgement

This work was supported by the ITEA M2MGrids Project, grant number ITEA141011, and by the Spanish Ministry of Economy and Competitiveness grants TIN2016-80622-P (AEI/FEDER, UE) and TIN2014-61627-EXP. Many thanks to Mehmet Gönen for his support on machine learning techniques.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Reyhan Aydoğan.

Additional information

Dr. Reyhan Aydoğan is an assistant professor at Özyegin University, Istanbul and guest researcher in Interactive Intelligence Group at Delft University of Technology, the Netherlands. She received her PhD in computer science from Boğaziçi University in 2011. After then she has worked at Delft University of Technology for 6 years. As a visiting scholar, she has been at Massachusetts Institute of Technology, Norwegian University of Science and Technology and Nagoya Institute of Technology. Her research focuses on the modeling, development and analysis of agent technologies that integrate different aspects of intelligence such as reasoning, decision making and learning. She is applying artificial intelligence techniques such as machine learning and semantic reasoning in designing and developing agent-based decision support systems, particularly negotiation support systems and automated negotiation tools. Dr. Aydoğan is one of the main organizers of the International Automated Negotiating Agents Competition (ANAC). She co-organized the following workshops: Conflict Resolution in Decision Making Workshop (COREDEMA) in PAAMS 2013, ECAI 2016, and IJCAI 2017; The Workshop on Agent-based Complex Automated Negotiations (ACAN) in AAMAS 2015-2017. She is serving as a program committee member in reputable conferences such as AAMAS, IJCAI, and ECAI.

Dr. Ivan Marsa-Maestre is an associate professor at the Computer Engineering Department of the University of Alcala in Spain. He received his telecommunication engineering degree from the University of Alcala in 2003 and the Ph.D. in from the University of Alcala in 2009. His research interests focus on the use of negotiation and nonlinear optimization techniques for distributed coordination of complex systems, such as computer networks, supply chains or vehicle management systems. He has taken part in many public and private research projects in these matters, has a number of publications in high impact international conferences and journals, and serves as program chair and reviewer for some of them. From his research have emerged collaborative research lines with international research groups like the Center for Green Computing, at the Nagoya Institute of Technology (Japan), the Technical University of Delft (TUDelft) or the Center for Collective Intelligence, at the Massachusetts Institute of Technology (USA).

Dr. Mark Klein (http://cci.mit.edu/klein/) is a principal research scientist at the MIT Center for Collective Intelligence. He received his PhD in Artificial Intelligence from the University of Illinois in 1989, and since then has worked for the Hitachi Advanced Research Laboratory, Boeing Research, Pennsylvania State University and (for the last 20 years) the Massachusetts Institute of Technology. He has also had visiting appointments at the Nagoya Institute of Technology, the National Institute of Advanced Industrial Science and Technology, the University of Hong Kong, Otago University, the University of Naples, and the University of Zurich, among others. His research draws from such fields as computer science, economics, operations research, and complexity science to develop and evaluate computer technologies that enable greater ‘collective intelligence’ in large groups faced with complex decisions. His current projects focus on large-scale on-line deliberation, as well as negotiation protocols for complex problems with many interdependent issues. He has also made contributions in the areas of computer-supported conflict management for collaborative design, design rationale capture, business process re-design, exception handling in workflow and multi-agent systems, and service discovery. He has nearly 200 publications in these areas, with over eight thousand citations on google scholar and an h-index of 43. He serves on the editorial boards of six journals related to AI and social computing, as well as on the program committees for the premier conferences in those areas.

Catholijn Jonker is full professor of Interactive Intelligence (0.8 fte) at the Faculty of Electrical Engineering, Mathematics and Computer Science of the Delft University of Technology and full professor of Explainable Artificial Intelligence (0.2 fte) at the Leiden Institute for Advanced Computer Science of Leiden Universit. She received her PhD in computer science from Utrecht University in 1994. She chaired De Jonge Akademie (Young Academy) of the KNAW (The Royal Netherlands Society of Arts and Sciences) in 2005 and 2006, and she was a member of the same organization from 2005 to 2010. She is a member of the Koninklijke Hollandsche Maarschappij der Wetenschappen and of the Academia Europaea. She was the president of the National Network Female Professors (LNVH) in The Netherlands from September 2013 till January 2016. Catholijn is EurAI Fellow since 2015, and EurAI board member since 2016, EurAI is the European Association for Artificial Intelligence.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Aydoğan, R., Marsa-Maestre, I., Klein, M. et al. A Machine Learning Approach for Mechanism Selection in Complex Negotiations. J. Syst. Sci. Syst. Eng. 27, 134–155 (2018). https://doi.org/10.1007/s11518-018-5369-5

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11518-018-5369-5

Keywords

  • Automated negotiation
  • mechanism selection
  • scenario metrics