Methods, apparatuses, and systems for data mapping

1. An apparatus comprising at least one processor and at least one non-transitory memory comprising program code, wherein the at least one non-transitory memory and the program code are configured to, with the at least one processor, cause the apparatus to at least:

retrieve a first plurality of data objects associated with a first database schema from a database;

determine, based at least on the first plurality of data objects, a first data classifier corresponding to the first database schema using a first machine learning model configured based at least in part on correlation metadata indicating a relationship between at least the first database schema from the database and at least one other database schema;

generate a mapping specification based at least in part on the first data classifier and the first plurality of data objects, wherein the mapping specification comprises one or more rule statements that specifies a movement and/or transformation to determine representation of a second plurality of data objects associated with a second database schema based on the first plurality of data objects associated with the first database schema, wherein the mapping specification is configured to convert the first plurality of data objects associated with the first database schema to the second plurality of data objects associated with the second database schema, wherein the mapping specification is configured to split a combined data portion of the first database schema into a plurality of portions of the second database schema; and

generate the second plurality of data objects based at least in part on the first plurality of data objects and the mapping specification.

2. The apparatus of claim 1 , wherein the first plurality of data objects comprise a first data table, wherein the first data table comprises at least one data field.

3. The apparatus of claim 2 , wherein the first data table comprises at least one of name metadata, column metadata, or row metadata.

4. The apparatus of claim 3 , wherein, when determining the first data classifier corresponding to the first database schema, the at least one non-transitory memory and the program code are configured to, with the at least one processor, cause the apparatus to:

retrieve at least one of the name metadata, the column metadata, or the row metadata associated with the first plurality of data objects; and

determine the first data classifier based further on at least one of the name metadata, the column metadata, or the row metadata.

5. The apparatus of claim 2 , wherein the first plurality of data objects comprise a second data table, wherein the at least one non-transitory memory and the program code are configured to, with the at least one processor, cause the apparatus to:

determine correlation metadata associated with the first data table and the second data table; and

determine the first data classifier based further on the correlation metadata.

6. The apparatus of claim 2 , wherein, when determining the first data classifier corresponding to the first database schema, the at least one non-transitory memory and the program code are configured to, with the at least one processor, cause the apparatus to:

determine domain metadata associated with the first data table; and

determine the first data classifier based further on the domain metadata.

7. The apparatus of claim 1 , wherein, prior to generating the mapping specification, the at least one non-transitory memory and the program code are configured to, with the at least one processor, cause the apparatus to further:

calculate a confidence score associated with the first data classifier; and

determine whether the confidence score satisfies a predetermined threshold.

8. The apparatus of claim 1 , the apparatus further caused to:

calculate a confidence score associated with the first data classifier;

generate feedback data from an expert user indicating whether the first data classifier is accurate for the first plurality of data objects, wherein the expert user differs from an end user associated with the mapping specification; and

update training of the first machine learning model based at least in part on the feedback data.

9. The apparatus of claim 8 , wherein the confidence score comprises a proximity value between at least one data field of the first plurality of data objects and training data associated with a supervised learning model.

10. The apparatus of claim 1 , wherein the correlation metadata comprises domain metadata, wherein the first machine learning model is configured based at least in part on the domain metadata.

11. The apparatus of claim 1 , wherein the first data classifier is determined based at least in part on resulting data generated by processing a particular data object utilizing at least one natural language processing model.

12. The apparatus of claim 1 , wherein the first machine learning model comprises a decision tree that includes at least one leaf corresponding to the first data classifier and at least one other leaf corresponding to a second possible data classifier.

13. A computer-implemented method, comprising:

retrieving a first plurality of data objects associated with a first database schema from a database;

determining, based at least on the first plurality of data objects, a first data classifier corresponding to the first database schema using a first machine learning model configured based at least in part on correlation metadata indicating a relationship between at least the first database schema from the database and at least one other database schema;

generating a mapping specification based at least in part on the first data classifier and the first plurality of data objects, wherein the mapping specification comprises one or more rule statements that specifies a movement and/or transformation to determine representation of a second plurality of data objects associated with a second database schema based on the first plurality of data objects associated with the first database schema, wherein the mapping specification is configured to convert the first plurality of data objects associated with the first database schema to the second plurality of data objects associated with the second database schema, wherein the mapping specification is configured to split a combined data portion of the first database schema into a plurality of portions of the second database schema; and

generating the second plurality of data objects based at least in part on the first plurality of data objects and the mapping specification.

14. The computer-implemented method of claim 13 , wherein the first plurality of data objects comprise a first data table, wherein the first data table comprises at least one data field.

15. The computer-implemented method of claim 14 , wherein the first data table comprises at least one of name metadata, column metadata, or row metadata.

16. The computer-implemented method of claim 15 , wherein determining the first data classifier corresponding to the first database schema further comprises:

retrieving at least one of the name metadata, the column metadata, or the row metadata associated with the first plurality of data objects; and

determining the first data classifier based further on at least one of the name metadata, the column metadata, or the row metadata.

17. The computer-implemented method of claim 14 , wherein the first plurality of data objects comprise a second data table, wherein the computer-implemented method further comprises:

determining correlation metadata associated with the first data table and the second data table; and

determining the first data classifier based further on the correlation metadata.

18. The computer-implemented method of claim 14 , further comprising:

determining domain metadata associated with the first data table; and

determining the first data classifier based further on the domain metadata.

19. The computer-implemented method of claim 13 , further comprising:

calculating a confidence score associated with the first data classifier; and

determining whether the confidence score satisfies a predetermined threshold.

20. A computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising an executable portion configured to:

retrieve a first plurality of data objects associated with a first database schema from a database,

determine, based at least on the first plurality of data objects, a first data classifier corresponding to the first database schema using a first machine learning model configured based at least in part on correlation metadata indicating a relationship between at least the first database schema from the database and at least one other database schema;

generate a mapping specification based at least in part on the first data classifier and the first plurality of data objects, wherein the mapping specification comprises one or more rule statements that specifies a movement and/or transformation to determine representation of a second plurality of data objects associated with a second database schema based on the first plurality of data objects associated with the first database schema, wherein the mapping specification is configured to convert the first plurality of data objects associated with the first database schema to the second plurality of data objects associated with the second database schema, wherein the mapping specification is configured to split a combined data portion of the first database schema into a plurality of portions of the second database schema; and

generate the second plurality of data objects based at least in part on the first plurality of data objects and the mapping specification.