“Dirty” data is data that is inaccurate, inconsistent, or contains errors that make it inappropriate to use for analysis or decision-making. Dirty data can arise from a variety of sources, such as human error, invalid assumptions, defects, temporary loss of connectivity, or incomplete data sets. At Kohort, we have implemented a robust, automated Data Validation process that sense-checks all inbound data and provides clear and informative errors and warnings, allowing our ingestion team and the client to work together to resolve any dirty data issues as quickly as possible. This ensures our forecasts are always based on the best quality data.