Many recommendation techniques have been developed over the past decade, and major efforts in both academia and industry have been made to improve recommendation accuracy. However, it has been increasingly noted that it is not sufficient to have accuracy as the sole criteria in measuring recommendation quality, and consider other important dimensions, such as diversity, confidence, and trust, to generate recommendations that are not only accurate but also useful to users. More diverse recommendations, presumably leading to more sales of long-tail items, could be beneficial for both individual users and some business models. The main aim of this paper is to find the best top-N recommendation lists for all users according to two measures, they are accuracy and diversity. To get maximum diversity, optimization based approaches are used while maintaining acceptable levels of accuracy in the proposed method.