Estimating negotiation agreement zone using support vector machine with genetic algorithm

Choosing the right counterpart can have a significant impact on negotiation success. Unfortunately, little research has studied in such negotiation counterpart decisions. The purpose of this study is to develop negotiation agents that can behave rationally so as to improve the final outcomes, these agents employ support vector machine empowered by genetic algorithm with the same strategy used before. Results from the experimental work show that the performance of the strategies improved is promising when it is compared with the results of the same strategies without using these mining techniques. It also showed that having previous knowledge about the opponent's preferences and constraints, negotiation agents can achieve more optimal outcomes in decreased offers. Moreover, the study showed that the influence of favourable past negotiated agreement on preferences has a great impact on selecting the optimal offers so as to lead the negotiation to "win-win" outcomes raising the utility profit results (if applicable) in the future.