This volume contains the papers presented at LEARNER 2017: the 1st International Workshop on LEARning Next gEneration Rankers, co-located with the third ACM International Conference on the Theory of Information Retrieval, (ICTIR 2017) held in Amsterdam, The Netherlands, on October 1, 2017. The workshop aimed at bringing together researchers from Information Retrieval (IR), Machine Learning (ML), and related application areas, to investigate new solutions for Learning to Rank (LtR). The inner core of IR has always been centered around the ranking, i.e. how to properly order documents by estimating their relevance with respect to a given query. Nowadays, documents, information needs, and queries are getting more and more complex and diversi ed, and this calls for more and more sophisticated techniques able to cope with this emerging complexity and the high expectations of users. ML, and in particular LtR, represent an e ective solution to address these challenges and to improve over state-of-the-art traditional algorithms. The goal of the workshop was to investigate how to improve ranking, in particular LtR, by bringing in new perspectives which have not been explored or fully addressed yet. Therefore, the workshop solicited the submission of contributions covering new approaches for LtR, evaluation of LtR algorithms, creation and curation of datasets for LtR, and application of LtR to speci c domains. The workshop involved 8 paper presentations, 4 full papers and 4 short papers, and two keynote presentations. This volume comprises a revised version of some of the presented papers and keynotes. We would like to express our special thanks to the Program Committee members, the keynote speakers { Craig Macdonald and Djoerd Hiemstra { the authors and all the attendees.