Abstract: The customers’ needs in a software project are identified in the process of software requirements elicitation. For developing a software system, this process is considered as one of the most important parts. In this part, it is decided precisely what will and when will be built. A close interaction between developers and end-users of the system is needed by requirements’ gathering. Meetings can be costly, inconvenient and infrequent if developers and end-users are in different organizations or different locations. The quality of the elicited requirements can greatly be impacted if there is a problem of communication. The miscommunication is leads the project failure. Requirement elicitation is a process difficult to scale to large software projects with many stakeholders which involves identifying and prioritizing requirements. A stakeholder is an individual or a group who can influence or be influenced by the success or failure of a project. In the existing methods to identify and prioritize requirements do not scale well to big projects. The large scale projects tend to be set by three problems: information overload, inadequate stakeholder input and biased prioritization of requirements. Existing methods to identify and prioritize requirements do not scale well to large projects. Existing requirements prioritization methods require substantial efforts from the requirements engineers when there are many requirements. To address the problems stakeholder recommender model will contain the following steps: identify the large project, analysis of requirements, identify and prioritize stakeholders, predict requirements, prioritize requirements. For making predictions, our approach will use one of the most well known algorithms that is k-Nearest Neighbor (kNN) algorithm. KNN is used to identify like-minded users with similar rating histories in order to predict ratings for unobserved users-item pairs, i.e., preprocessing. A unique subset of the community for each user is found out by KNN by identifying those with similar interests. To do so, every pair of user profile is compared to measure the degree of similarity. A neighbourhood is created for each user by selecting the k most similar users. The similarity between each pair of user profiles for users in the neighbourhood is used to compute predicted ratings from any range. Finally, the predicted ratings for the items are sorted according to the predicted value and the top-N items are proposed to the user as recommendations where N is the number of items recommended to the user.