2nd Workshop on Learning with Imbalanced Domains: Preface

This volume contains the Proceedings of the Second International Workshop on Learning with Imbalanced Domains: Theory and Applications LIDTA2018. This Workshop was coorganised by the Faculty of Computer Science of the Dalhousie University, Halifax, Canada, the Department of Computer Science of the American University, Washington DC, USA, the Department of Computer Science of the Virginia Commonwealth University, Richmond VA, USA and the Laboratory of Artificial Intelligence and Decision Support INESC TEC and Department of Computer Science, Faculty of Sciences of the University of Porto, Portugal. The Workshop was co-located with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD) 2018 and was held on the 10th of September 2018 in the Croke Park Conference Centre in Dublin, Ireland. The LIDTA 2018 Workshop focused on theoretical and practical aspects of the problem of learning from imbalanced domains. For a diverse and vast set of real-world applications, the end-user is interested in obtaining predictive models that reflect her/his non-uniform preferences over the target variable domain. In imbalanced domains the target variable values that have more value to the end-user are scarcely represented in the available training data. Moreover, these least-common values are often associated with events that are highly relevant and with potentially high costs and/or benefits. Examples of real-world applications where this problem occurs include different domains such as financial (e.g. unusual returns