Official statistics are characterised by the legally stipulated or self-imposed obligation to ensure the quality of their institutions, processes and products. The fitness for use of the products is the goal and promise of statistical offices. To this end, it adheres to European quality guidance, which is operationalised at the national level in the form of quality manuals. Hitherto, these have been designed and interpreted with the requirements of ‘classical’ statistical production processes in mind. Thus, in order to ensure continued adherence to quality standards, tailored quality guidance must be developed to accompany the increasing use of machine learning (ML) methods in official statistics. This chapter sets out a multistep approach towards achieving such guidance for ML. Taking the first two such steps, it builds on previous work to suggest six quality dimensions for ML, along with a list of specific quality guidelines that must be implemented to ensure quality along those dimensions.