Learning etl rules by example

A non-transitory computer readable medium having instructions stored thereon that, when executed by a processor, cause the processor to learn extract, transform, and load (“ETL”) mappings by example, the learning comprising:

• extracting a plurality of features from a source schema and a target schema, the features comprising at least columns of a plurality of tables of the source schema and the target schema;
• providing example ETL mappings to a machine learning algorithm, wherein the example ETL mappings comprise definitions for extracting data from one or more tables of the source schema and loading the extracted data into one or more tables of the target schema;
• predicting, using the machine learning algorithm and based on the source schema, target schema, and extracted features, one or more ETL rules that define logic for extracting data from the source schema and loading the extracted data into the target schema;
• and
• generating additional ETL mappings based on the predicted ETL rules, the source schema, the target schema, and the extracted features, the additional ETL mappings providing additional definitions for extracting data from one or more tables of the source schema and loading the extracted data into one or more tables of the target schema.

A system comprising:

• a processing device in communication with a memory device, the processing device configured to learn extract, transform, and load (“ETL”) mappings by example, the learning comprising:
• extracting a plurality of features from a source schema and a target schema, the features comprising at least columns of a plurality of tables of the source schema and the target schema;
• providing example ETL mappings to a machine learning algorithm, wherein the example ETL mappings comprise definitions for extracting data from one or more tables of the source schema and loading the extracted data into one or more tables of the target schema;
• predicting, using the machine learning algorithm and based on the source schema, target schema, and extracted features, one or more ETL rules that define logic for extracting data from the source schema and loading the extracted data into the target schema;
• and
• generating additional ETL mappings based on the predicted ETL rules, the source schema, the target schema, and the extracted features, the additional ETL mappings providing additional definitions for extracting data from one or more tables of the source schema and loading the extracted data into one or more tables of the target schema.