Unsupervised analytical review

• US 20140279301A1
• Filed: 03/14/2013
• Published: 09/18/2014
• Est. Priority Date: 02/20/2012
• Status: Active Grant

• Current Assignee: Galisteo Consulting Group, Inc.
• Original Assignee: Galisteo Consulting Group, Inc.
• Inventors: Chew, Peter Alexander
• Granted Patent: US 9,037,607 B2
• Time in Patent Office: Days
• US Class Current: 705/30
• CPC Class Codes: G06F 16/273 Asynchronous replication or reconciliation
• CPC Class Codes: G06Q 40/10 Tax strategies

Abstract

Disclosed is a method generally applicable to any financial dataset for the purposes of: (1) determining the most important patterns in the given dataset, in order of importance; (2) determining any trends in those patterns; (3) determining relationships between patterns and trends; and (4) allowing quick visual identification of anomalies for closer audit investigation. These purposes generally fall within the scope of what in financial auditing is known as ‘analytical review’. The current method'"'"'s advantages over existing methods are that is fully independent of the financial data subject to analysis, requires no background knowledge of the target business or industry, and is both scalable (to large datasets) and fully scale-invariant, requiring no a priori notion of financial materiality. These advantages mean, for example, that the same method can be by an external auditor for many different clients with virtually no client-specific customization, directing his attention to the areas where more detailed audit investigation may be required. Compared with existing methods, the current method is extremely flexible, and because it requires no a priori knowledge, saves significant time in understanding the fundamentals of a business.

Claims

1. A computer implemented method of analytical review, comprising:

a computer having a financial dataset stored thereon;

the computer extracting features of each transaction in the dataset;

the computer generating a transaction-by-attribute/value matrix;

the computer applying weights to the transaction-by-attribute/value matrix to generate a weighted transaction-by-attribute/value matrix;

the computer factorizing the weighted transaction-by-attribute/value matrix; and

the computer generating output enabling significant patterns and trends to be identified;

wherein the extracting, generating of a matrix, applying weights, factorizing, and generating of output are performed regardless of the number, type, or monetary amount of transactions, regardless of the number or type of features associated with each transaction, and regardless of the provenance of the dataset.

2. A computer implemented method of claim 1, wherein extracting features of each transaction in the dataset comprises unpivoting the dataset to create a list of transactions associated with attribute/values.

3. A computer implemented method of claim 1, wherein extracting features comprises:

tokenizing contents of fields in the dataset which contain unstructured text to create a list of transactions associated with text tokens; and

treating the text tokens as attribute/values.

4. A computer implemented method of claim 1, wherein generating a transaction-by-attribute/value matrix comprises:

listing unique transactions along one axis of the matrix;

listing unique attribute/values along another axis of the matrix; and

populating the matrix with non-zero values recording a number of times particular attribute/values occur in conjunction with particular transactions.

5. A computer implemented method of claim 1, wherein applying weights to the transaction-by-attribute/value matrix comprises:

calculating a distinctiveness weighting by measuring pointwise mutual information between respective transactions and attribute/values which occur in conjunction with one another; and

creating a weighted transaction-by-attribute/value matrix identical to the transaction-by-attribute/value matrix except that values in the weighted transaction-by-attribute/value matrix are the distinctiveness weightings instead of a number of times particular attribute/values occur in conjunction with particular transactions.

6. A computer implemented method of claim 5, wherein applying weights to the transaction-by-attribute/value matrix comprises:

calculating a materiality weighting equal to a logarithm of each transaction'"'"'s absolute monetary amount, for transactions with a non-zero monetary amount; and

updating the weighted transaction-by-attribute/value matrix so that values in the weighted transaction-by-attribute/value matrix are the distinctiveness weighting plus the materiality weighting.

7. A computer implemented method of claim 1, wherein factorizing the weighted transaction-by-attribute/value matrix comprises:

performing a truncated or full singular value decomposition on the weighted transaction-by-attribute/value matrix; and

generating a transaction-by-concept matrix as an output of the singular value decomposition.

8. A computer implemented method of claim 1, wherein generating output comprises:

creating a series of scatterplots, one per concept;

creating one axis for each scatterplot to correspond to a logical ordering of transactions;

creating another axis for each scatterplot to correspond to importance in the concept; and

representing transactions as individual points on the scatterplots.

9. A computer implemented method of claim 1, wherein generating output comprises creating a table of transactions which lists importance of the transactions in each dimension of the factorization.

10. A computer implemented method of financial anomaly detection, comprising:

a computer having a financial dataset stored thereon;

the computer extracting features of each transaction in the dataset;

the computer generating a transaction-by-attribute/value matrix;

the computer applying weights to the transaction-by-attribute/value matrix to generate a weighted transaction-by-attribute/value matrix;

the computer factorizing the weighted transaction-by-attribute/value matrix; and

the computer generating output enabling anomalies to be identified;

wherein the extracting, generating of a matrix, applying weights, factorizing, and generating of output are performed regardless of the number, type, or monetary amount of transactions, regardless of the number or type of features associated with each transaction, and regardless of the provenance of the dataset.

11. A computer implemented method of claim 10, wherein extracting features of each transaction in the dataset comprises unpivoting the dataset to create a list of transactions associated with attribute/values.

12. A computer implemented method of claim 10, wherein extracting features comprises:

tokenizing contents of fields in the dataset which contain unstructured text to create a list of transactions associated with text tokens; and

treating the text tokens as attribute/values.

13. A computer implemented method of claim 10, wherein generating a transaction-by-attribute/value matrix comprises:

listing unique transactions along one axis of the matrix;

listing unique attribute/values along another axis of the matrix; and

populating the matrix with non-zero values recording a number of times particular attribute/values occur in conjunction with particular transactions.

14. A computer implemented method of claim 10, wherein applying weights to the transaction-by-attribute/value matrix comprises:

calculating a distinctiveness weighting by measuring pointwise mutual information between respective transactions and attribute/values which occur in conjunction with one another; and

creating a weighted transaction-by-attribute/value matrix identical to the transaction-by-attribute/value matrix except that values in the weighted transaction-by-attribute/value matrix are the distinctiveness weightings instead of a number of times particular attribute/values occur in conjunction with particular transactions.

15. A computer implemented method of claim 14, wherein applying weights to the transaction-by-attribute/value matrix comprises:

calculating a materiality weighting equal to a logarithm of each transaction'"'"'s absolute monetary amount, for transactions with a non-zero monetary amount; and

updating the weighted transaction-by-attribute/value matrix so that values in the weighted transaction-by-attribute/value matrix are the distinctiveness weighting plus the materiality weighting.

16. A computer implemented method of claim 10, wherein factorizing the weighted transaction-by-attribute/value matrix comprises:

performing a truncated or full singular value decomposition on the weighted transaction-by-attribute/value matrix; and

generating a transaction-by-concept matrix as an output of the singular value decomposition.

17. A computer implemented method of claim 10, wherein generating output comprises:

creating a series of scatterplots, one per concept;

creating one axis for each scatterplot to correspond to a logical ordering of transactions;

creating another axis for each scatterplot to correspond to a range of values in the output of factorization; and

representing transactions as individual points on the scatterplots.

18. A computer implemented method of claim 10, wherein generating output comprises tabulating transactions in order of their importance in each dimension of the factorization.

19. A method of analytical review and anomaly detection, comprising the steps of:

extracting features of each transaction in a financial dataset;

generating a transaction-by-attribute/value matrix;

applying weights to the transaction-by-attribute/value matrix to generate a weighted transaction-by-attribute/value matrix;

factorizing the weighted transaction-by-attribute/value matrix; and

generating output so as to transform the dataset into useful actionable information enabling identification of transactions or groups of transactions that merit closer scrutiny;

wherein the extracting, generating of a matrix, applying weights, factorizing, and generating of output are performed regardless of the number, type, or monetary amount of transactions, regardless of the number or type of features associated with each transaction, and regardless of the provenance of the dataset.

20. The method of financial account reconciliation of claim 19, further providing instructions that, when executed by a computer, will cause the computer to perform further operations, comprising:

extracting features of each transaction in a financial dataset;

generating a transaction-by-attribute/value matrix;

applying weights to the transaction-by-attribute/value matrix to generate a weighted transaction-by-attribute/value matrix;

factorizing the weighted transaction-by-attribute/value matrix;

generating output enabling anomalies to be identified.