The aim of this project is to extend and speed up data validation at the Swiss Federal Statistical Office (FSO) by means of machine learning algorithms and to improve data quality. Statistical offices carry out data validation (DV) to check the quality and reliability of administrative data and survey data. Data that are likely to be incorrect are sent back to data suppliers with a correction request. Until now, such DV have mainly been carried out at two different levels: either through manual checks or automated processes using threshold values and logical tests. This process of two-way “plausibility checks” involves a great deal of work. In some cases, staff is required to manually check the data again, in other cases rules are applied that often require additional checks. This rule-based approach has developed from previous experience but is not necessarily exhaustive and always precise. Machine learning has the potential to ensure faster and more accurate checks. This project is one of the five (pilot) projects currently being developed in line with FSO’s data innovation strategy (FSO, 2017) with the goal to augment and/or complement the existing basic official statistical production at the FSO.