Regression Models for Ordinal Data : AMachine Learning

In contrast to the standard machine learning tasks of classi cation and metric regression we investigate the problem of predicting variables of ordinal scale, a setting referred to as ordinal regression. The task of ordinal regression arises frequently in the social sciences and in information retrieval where human preferences play a major role. Also many multi{class problems are really problems of ordinal regression due to an ordering of the classes. Although the problem is rather novel to the Machine Learning Community it has been widely considered in Statistics before. All the statistical methods rely on a probability model of a latent (unobserved) variable and on the condition of stochastic ordering. In this paper we develop a distribution independent formulation of the problem and give uniform bounds for our risk functional. The main di erence to classi cation is the restriction that the mapping of objects to ranks must be transitive and asymmetric. Combining our theoretical framework with results from measurement theory we present an approach that is based on a mapping from objects to scalar utility values and thus guarantees transitivity and asymmetry. Applying the principle of Structural Risk Minimization as employed in Support Vector Machines we derive a new learning algorithm based on large margin rank boundaries for the task of ordinal regression. Our method is easily extended to nonlinear utility functions. We give experimental results for an Information Retrieval task of learning the order of documents with respect to an initial query. Moreover, we show that our algorithm outperforms more naive approaches to ordinal regression such as Support Vector Classi cation and Support Vector Regression in the case of more than two ranks1.