System and methods are described for improving automated data discovery analysis in a cloud computing environment. A method includes receiving a request to analyze a data set stored in the memory device, the data set including one or more columns, the one or more columns including one or more data values in one or more cells of each column; classify each of the one or more columns as a type of column; for a selected one of the one or more columns, if the selected column's type is an external type, join one or more columns of an external knowledge base correlated to the selected column into the data set to create an expanded data set; and execute an automated data discovery model on the expanded data set.