Parallelizable distributed data preservation apparatuses, methods and systems
The Parallelizable Distributed Data Preservation Apparatuses, Methods and Systems (“PDDP”) transforms an ad impression event, a bidding invite, original data set, original data distribution estimation, symetry ML BET table inputs via PDDP components into real-time mobile bid, mobile ad placement, pseudo random datastet, build classifier structure, build regression structure outputs. In one example embodiment, the PDDP includes an apparatus. The PDDP's apparatus' instructions include obtaining original data set and determine appropriate symmetry ML basic element table, generating original data distribution estimation structure and generate new dataset random generation structure, generating new random dataset transformation structure and transforming original data with the symmetry ML basic element table into pseudo random dataset. The PDDP also provides pseudo random dataset to machine learning component and to generate build classifier and build regression structures from the machine learning component.
1. A real-time parallelized data integrity preservation apparatus, comprising:
at least one memory;
a component collection stored in the at least one memory;
any of at least one processor disposed in communication with the at least one memory, the any of at least one processor executing processor-executable instructions from the component collection, the component collection storage structured with processor-executable instructions comprising:
obtain an original dataset data structure from a plurality of data source types using a symmetry machine learning component;
determine, based on the obtained original dataset data structure, an appropriate type of symmetry machine learning basic element table;
generate original data distribution estimation data structure from the original dataset data structure;
generate new dataset random generation data structure from the original data distribution estimation data structure;
generate new random dataset transformation data structure by factorizing the new dataset random generation data structure;
transform the original dataset data structure with the symmetry machine learning basic element table and the new random dataset transformation data structure into a pseudo random dataset data structure;
provide the pseudo random dataset data structure to a machine learning component; and
generate build classifier and build regression structures from the machine learning component.
2. The apparatus of claim 1 , in which the basic element table contains correlation information of the original dataset.
3. The apparatus of claim 1 , in which, from the basic element table, a transform is used to estimate random data correlation.
4. The apparatus of claim 1 , in which the pseudo random dataset data structure is artificially correlated data and has a same second order correlation structure as the original dataset.
5. The apparatus of claim 4 , in which the second order correlation structure is at least one of linear correlation coefficient, variance and mean.
6. The apparatus of claim 1 , in which random data is first correlated using a principal component analysis matrix.
7. The apparatus of claim 1 , in which random data is first correlated using a Cholesky factorization matrix.
8. The apparatus of claim 1 , in which a random dataset is generated independently of the original dataset.
9. A real-time parallelized data integrity preservation processor-implemented system, comprising:
means to store a component collection;
means to process processor-executable instructions from the component collection, the component collection storage structured with processor-executable instructions including:
obtain an original dataset data structure from a plurality of data source types using a symmetry machine learning component;
determine, based on the obtained original dataset data structure, an appropriate type of symmetry machine learning basic element table;
generate original data distribution estimation data structure from the original dataset data structure;
generate new dataset random generation data structure from the original data distribution estimation data structure;
generate new random dataset transformation data structure by factorizing the new dataset random generation data structure;
transform the original dataset data structure with the symmetry machine learning basic element table and the new random dataset transformation data structure into a pseudo random dataset data structure;
provide the pseudo random dataset data structure to a machine learning component; and
generate build classifier and build regression structures from the machine learning component.
10. The system of claim 9 , in which the basic element table contains correlation information of the original dataset.
11. The system of claim 9 , in which, from the basic element table, a transform is used to estimate random data correlation.
12. The system of claim 9 , in which the pseudo random dataset data structure is artificially correlated data and has a same second order correlation structure as the original dataset.
13. The system of claim 12 , in which the second order correlation structure is at least one of linear correlation coefficient, variance and mean.
14. The system of claim 9 , in which random data is first correlated using a principal component analysis matrix.
15. The system of claim 9 , in which random data is first correlated using a Cholesky factorization matrix.
16. The system of claim 9 , in which a random dataset is generated independently of the original dataset.
17. A real-time parallelized data integrity preservation, processor-readable, non-transitory medium, the medium storing a component collection, the component collection storage structured with processor-executable instructions comprising:
obtain an original dataset data structure from a plurality of data source types using a symmetry machine learning component;
determine, based on the obtained original dataset data structure, an appropriate type of symmetry machine learning basic element table;
generate original data distribution estimation data structure from the original dataset data structure;
generate new dataset random generation data structure from the original data distribution estimation data structure;
generate new random dataset transformation data structure by factorizing the new dataset random generation data structure;
transform the original dataset data structure with the symmetry machine learning basic element table and the new random dataset transformation data structure into a pseudo random dataset data structure;
provide the pseudo random dataset data structure to a machine learning component; and
generate build classifier and build regression structures from the machine learning component.
18. The medium of claim 17 , in which the basic element table contains correlation information of the original dataset.
19. The medium of claim 17 , in which, from the basic element table, a transform is used to estimate random data correlation.
20. The medium of claim 17 , in which the pseudo random dataset data structure is artificially correlated data and has a same second order correlation structure as the original dataset.
21. The medium of claim 20 , in which the second order correlation structure is at least one of linear correlation coefficient, variance and mean.
22. The medium of claim 17 , in which random data is first correlated using a principal component analysis matrix.
23. The medium of claim 17 , in which random data is first correlated using a Cholesky factorization matrix.
24. The medium of claim 17 , in which a random dataset is generated independently of the original dataset.
25. A processor-implemented real-time parallelized data integrity preservation method, including processing processor-executable instructions via any of at least one processor from a component collection stored in at least one memory, the component collection storage structured with processor-executable instructions comprising:
obtaining, via any of at least one processor, an original dataset data structure from a plurality of data source types using a symmetry machine learning component;
determining, via the any of at least one processor, based on the obtained original dataset data structure, an appropriate type of symmetry machine learning basic element table;
generating, via the any of at least one processor, original data distribution estimation data structure from the original dataset data structure;
generating, via the any of at least one processor, new dataset random generation data structure from the original data distribution estimation data structure;
generating, via the any of at least one processor, new random dataset transformation data structure by factorizing the new dataset random generation data structure;
transforming, via the any of at least one processor, the original dataset data structure with the symmetry machine learning basic element table and the new random dataset transformation data structure into a pseudo random dataset data structure;
providing, via the any of at least one processor, the pseudo random dataset data structure to a machine learning component; and
generating, via the any of at least one processor, build classifier and build regression structures from the machine learning component.
26. The method of claim 25 , in which the basic element table contains correlation information of the original dataset.
27. The method of claim 25 , in which, from the basic element table, a transform is used to estimate random data correlation.
28. The method of claim 25 , in which the pseudo random dataset data structure is artificially correlated data and has a same second order correlation structure as the original dataset.
29. The method of claim 25 , in which the second order correlation structure is at least one of linear correlation coefficient, variance and mean.
30. The method of claim 25 , in which random data is first correlated using a principal component analysis matrix.
31. The method of claim 25 , in which random data is first correlated using a Cholesky factorization matrix.
32. The method of claim 25 , in which a random dataset is generated independently of the original dataset.