Machine Learning holds a great potential for statistical organisations. It can make the production of statistics more efficient by automating certain processes or assisting humans to carry out the processes. It also allows statistical organisations to use new types of data such as social media data and imagery.

Many national and international statistical organisations are exploring how machine learning can be used to increase the relevance and the quality of official statistics in an environment of growing demands for trusted information, rapidly developing and accessible technologies, and numerous competitors. While the specific business environments may vary depending on the country, these statistical organisations face similar types of challenges which can benefit from sharing knowledge, experiences and collaborating on developing common solutions within the broad official statistical community.

This publication presents the practical applications of machine learning in three working areas within statistical organisations and discusses their value added, challenges and lessons learned. It also includes a quality framework that could help guiding the choice of methods, challenges that arise when integrating machine learning into statistical production, and key steps for moving machine learning from the experimental stage to the production stage and concludes with key messages on advancing the use of machine learning for the production of official statistics.

This publication is based on the results from two international initiatives: the UNECE High-Level Group on Modernisation of Official Statistics (HLG-MOS) Machine Learning Project (2019-2020) and the United Kingdom’s Office for National Statistics (ONS) – UNECE Machine Learning Group 2021, and approved by the HLG-MOS.