Supervision : Zahia GUESSOUM

Co-supervision : DOCTOR Sylvain, ROUSSEL Olivier

A multiagent system for an invoice marketplace

For most companies, the time gap between the moment when they begin to spend money and the moment when they receive payment from their customer generates a working capital requirement. The latter may create issues such as contract lost or bankruptcy. In the current context, getting credits from banks may be either costly or even impossible for Small and Medium Enterprises. Indeed, many banks refuse to lend money for small companies or when they estimate that there is a risk. It is then possible to rely on other solutions as factoring and get immediate credit from the invoices.
In this thesis, we propose a factoring marketplace based on related to curious agents that try to infer private information from their partners. This kind of behavior is harmful both for the agents and for the platform more generally. We thus propose to design a negotiation protocol resistant to such behavior by endowing the agents with an incentive to negotiate only when they really try to get a good.
We then propose an automated negotiation agent which relies on Monte Carlo Tree Search techniques. Those techniques have proved to be quite efficient in AI for games. Our agent is able to learn information from its partner, though it is not its main objective in order to get to a beneficial agreement. For this purpose, it relies on opponent modeling techniques and machine learning such as Bayesian Learning and Gaussian Process Regression.

2016-2022 Publications

• 2022
  • C. Buron, Z. Guessoum, S. Ductor, O. Roussel : “MoCaNA, un agent de négociation automatique utilisant la recherche arborescente de Monte-Carlo”, Revue Ouverte d'Intelligence Artificielle, vol. 3 (5-6), Post-actes des Journées Francophones sur les Systèmes Multi-Agents, pp. 645-669, (Association pour la diffusion de la recherche francophone en intelligence artificielle) (2022)
• 2019
  • C. Buron, Z. Guessoum, S. Ductor : “MCTS-based Automated Negotiation Agent”, International Conference on Principles and Practice of Multi-Agent Systems (PRIMA), vol. 11873, Lecture Notes in Computer Science, Torino, Italy, pp. 186-201, (Springer) (2019)
  • C. Buron, Z. Guessoum, S. Ductor : “MCTS-based Automated Negotiation Agent (Extended Abstract)”, AAMAS 2019 - 18^th International Conference on Autonomous Agents and MultiAgent Systems, Montreal, Canada, pp. 1850-1852, (International Foundation for Autonomous Agents and Multiagent Systems) (2019)
  • C. Buron, S. Ductor, Z. Guessoum : “MoCaNA, an automated negotiation agent based on Monte Carlo Tree Search”, AAMAS 2019 - 18^th International Conference on Autonomous Agents and MultiAgent Systems, Montreal, Canada (2019)
• 2018
  • C. Buron : “Un système multi-agent pour une place de marché de factures”, thesis, phd defence 05/17/2018, supervision Guessoum, Zahia, co-supervision : Doctor, Sylvain, Roussel, Olivier (2018)
  • C. Buron, Z. Guessoum, S. Ductor, O. Roussel : “MoCaNA, un agent de négociation automatique utilisant la recherche arborescente de Monte-Carlo”, Vingt-sixièmes Journées Francophones sur les Systèmes Multi-Agents, Métabief, France (2018)
• 2016
  • C. Buron, S. Ductor, Z. Guessoum : “Marchandage et Curiosité”, 24^e Journées Francophones sur les Systèmes Multi-Agents (JFSMA 2016), Rouen, France (2016)
  • C. Buron, S. Ductor, Z. Guessoum : “Curiosity-Aware Bargaining”, European Starting AI Researcher Symposium (STAIRS), vol. 284, Frontiers in Artificial Intelligence and Applications, The Hague, Netherlands, pp. 27-38, (IOS Press) (2016)