(1) Title: GAMA (Genetic Algorithm driven Multi-Agents) for E-Commerce Integrative Negotiation ------------------------------------------------------------------------------------------------------------------ (2) 1st Author Name: Dr. Magda B. Fayek Address: Cairo University, Faculty of Engineering, Computer Engineering Department Phone: +2010 1589411 E-mail: magdafayek@gmail.com 2nd Author Name: Dr. Ihab A. Talkhan Address: Cairo University, Faculty of Engineering, Computer Engineering Department Phone: +2012 3105504 E-mail: italkhan@aucegypt.edu 3rd Author Name: Khalil S. El-Masry Address: 10 Zakaria Ahmed st., Azbakia, Cairo, Egypt 11111 Phone: +2012 1426146 E-mail: khalil_elmasry@yahoo.com ------------------------------------------------------------------------------------------------------------------ (3) Name: Khalil S. El-Masry ------------------------------------------------------------------------------------------------------------------ (4) ABSTRACT Software agents help automate a variety of tasks including those involved in buying and selling products over the internet. The need for handling complex highly configurable products, together with presenting important merchant value-added services gave rise to integrative negotiation protocols. In this paper we introduce GAMA, an agent-mediated shopping system that allows shoppers to consider merchant offerings’ full range of value in their buying decisions for complex products. The system helps shoppers through the two stages of product brokering and negotiation. Product Brokering is done through shopping agents adopting genetic algorithms to address the vast search space of product offerings. Integrative Negotiation is implemented using a “Collaborative GA” technique between both shopping and sales agents to satisfy the needs of both parties. The system has been simulated using the process of purchasing computers hardware. Results show that a high rate of satisfaction for both shoppers and merchants can be achieved using GAMA. ------------------------------------------------------------------------------------------------------------------ (5) D, G ------------------------------------------------------------------------------------------------------------------ (6) The system has been rigorously tested, performing 100 runs for each setting and applying standard performance analysis principles. The user (shopper) has been allowed to define his/her satisfaction in a very comprehensive way (MAUT + a very user friendly interface). The results show the remarkable effect of "collaboration" on stabilizing the performance with respect to increasing probability of success, relative to "standard" GA. Regarding the number of parameters to be configured, the diversity of the search space, and, on the other hand, the processing time (relative to that needed by a human), the results can be considered very satisfying. Referring to the eight criteria for establishing that an automatically created result is competitive with a human-produced result, the selection of products -that highly meet shoppers' preferences- by genetic programming and integrative negotiation satisfies the following two of the eight criteria: (D) The result is publishable in its own right as a new scientific result—independent of the fact that the result was mechanically created. (G) The result solves a problem of indisputable difficulty in its field. ------------------------------------------------------------------------------------------------------------------ (7) Dr. Magda B. Fayek, Dr. Ihab A. Talkhan, Khalil S. El-Masry. GAMA (Genetic Algorithm driven Multi-Agents) for E-Commerce Integrative Negotiation. GECCO 2009 Proceedings. ------------------------------------------------------------------------------------------------------------------ (8) Any prize money, if any, is to be divided equally among the co-authors. ------------------------------------------------------------------------------------------------------------------ (9) The application is very innovative tackling a very hot issue on the internet (especially, at this age of social networks), i.e. the issue of "collaboration" and in particular "negotiations". Not only is it crucial for e-commerce but it can further be extended to other applications. It is interesting becasue it may uncover solutions not forseen by human negotiators bridging misunderstandings and conflicts, on a win-win basis. ------------------------------------------------------------------------------------------------------------------