Data interpretation analysis
Quality associated with an interpretation of data captured as unstructured data can be determined. Attributes can be identified within the unstructured data automatically. Subsequently, sentiment associated with each of the attributes can be determined based on the unstructured data. Correctness of the unstructured data, and thus the interpretation, can be assessed based on a comparison of the attribute and associated sentiment with structured data. A quality score can be generated that captures the quality of the data interpretation in terms of correctness and as well as results of another analysis including completeness, among others. Comparison of the quality score to a threshold can dictate whether or not the interpretation is subject to further review.
1. A computer implemented method comprising:
receiving unstructured data comprising a comment associated with a loan application;
identifying attributes of the comment;
determining sentiment of the attributes;
comparing the attributes and sentiment to structured data related to prior loan applications;
determining an accuracy score based on the comparison,
wherein the accuracy score captures deviation of the attributes and sentiment from the structured data; and
flagging the unstructured data for further review when the accuracy score falls below a predetermined acceptable-accuracy threshold.
2. The computer implemented method of claim 1 , further comprising identifying credit attributes.
3. The computer implemented method of claim 1 , further comprising determining the sentiment in terms of attribute strength or risk.
4. The computer implemented method of claim 1 , further comprising performing pattern recognition to identify the attributes.
5. The computer implemented method of claim 1 , further comprising computing the accuracy score based on a number of attributes and associated sentiment that match attributes computed from structured data from an application.
6. The computer implemented method of claim 1 , further comprising determining a quantity of attributes present in the unstructured data and generate a completeness score based on comparison with a predetermined threshold quantity of attributes.
7. The computer implemented method of claim 1 , further comprising computing an overall sentiment from the sentiment associated with each attribute and compare the overall sentiment with a judgement to assess the judgement in terms of consistency with the overall sentiment.
8. A system comprising:
a processor configured to:
receive unstructured data comprising a comment associated with a loan application;
identify attributes of the comment;
determine sentiment of the attributes;
compare the attributes and sentiment to structured data related to prior loan applications;
determine an accuracy score based on the comparison,
wherein the accuracy score captures deviation of the attributes and sentiment from the structured data; and
flag the unstructured data for further review when the accuracy score falls below a predetermined acceptable-accuracy threshold.
9. The system of claim 8 , wherein the processor is further configured to identify credit attributes.
10. The system of claim 8 , wherein the processor is further configured to determine the sentiment in terms of attribute strength or risk.
11. The system of claim 8 , wherein the processor is further configured to perform pattern recognition to identify the attributes.
12. The system of claim 8 , wherein the processor is further configured to compute the accuracy score based on a number of attributes and associated sentiment that match attributes computed from structured data from an application.
13. The system of claim 8 , wherein the processor is further configured to determine a quantity of attributes present in the unstructured data and generate a completeness score based on comparison with a predetermined threshold quantity of attributes.
14. The system of claim 8 , wherein the processor is further configured to compute an overall sentiment from the sentiment associated with each attribute and compare the overall sentiment with a judgement to assess the judgement in terms of consistency with the overall sentiment.
15. A non-transitory computer readable medium comprising program code that when executed by one or more processors is configured to cause the one or more processors to:
receive unstructured data comprising a comment associated with a loan application;
identify attributes of the comment;
determine sentiment of the attributes;
compare the attributes and sentiment to structured data related to prior loan applications;
determine an accuracy score based on the comparison,
wherein the accuracy score captures deviation of the attributes and sentiment from the structured data; and
flag the unstructured data for further review when the accuracy score falls below a predetermined acceptable-accuracy threshold.
16. The non-transitory computer readable medium of claim 15 , further comprising program code that when executed by the one or more processors is configured to cause the one or more processors to identify credit attributes.