Active learning is a process whereby students engage in activities, such as reading, writing, discussion, or problem solving that promote analysis, synthesis, and evaluation of class content. Cooperative learning, problem-based learning, and the use of case methods and simulations are some approaches that promote active learning. The quality of a ranking model highly depends on training data, including both the quantity and quality of the given pairwise constraints. It is a model of instruction that focuses the responsibility of learning on learners. Any system that presents ordered results to users is performing ranking. This has led to extensive interest in using machine learning techniques for learning a ranking retrieval function. An effective ranking function is the key component for many information retrieval systems, such as web search, collaborative filtering, image retrieval, and computational advertising. In this project, the system proposes a general active learning framework, Expected Loss Optimization (ELO), for ranking. It is applicable to a wide range of ranking functions. The key idea of the proposed framework is that given a loss function, the samples minimizing the expected loss are the most informative ones. Under this framework, we derive a novel active learning algorithm for ranking, which uses function ensemble to select most informative examples that minimizes a chosen loss.