Webstation: configurable web-based workstation for reason driven data analysis

• US 7,418,431 B1
• Filed: 09/27/2000
• Issued: 08/26/2008
• Est. Priority Date: 09/30/1999
• Status: Active Grant

• Current Assignee: Fair Isaac Corporation
• Original Assignee: Fair Isaac Corporation
• Inventors: Pathria, Anu K., Nies, Craig A., Deo, Arati S., Biafore, Louis S., de Traversay, Jean
• Primary Examiner(s): Holmes; Michael B
• Application Number:
  US09/672,142
• Time in Patent Office: 2,890 Days
• Field of Search: 707/1, 707/3, 707/5, 707/100, 705/22, 706/45, 706/46, 706/60, 706/62, 706/61
• US Class Current: 706/21
• CPC Class Codes: G06F 16/972 Access to data in other repository systems, e.g. legacy data or dynamic Web page generation
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling

Abstract

A system, computer program product, and method provide for reason driven data analysis in a web-based system that is configurable to various types of data and environments. The computer program product provides for navigation of a report tree of reports that are hierarchically organized with respect to reasons derived from an analysis of transactional data in a database. A frame based interface provides for easy and flexible navigation and configuration of the reports and other features. A configuration file is used to rapidly develop and customize the web-based system. Case management functionality is included to allow for management of cases being reviewed using the system.

Claims

1. A computer implemented method of analyzing results of a predictive model applied to a data pertaining to a plurality of entities, the method comprising:

providing a predictive model for scoring the entities;

displaying a rank ordering at least some of the entities according to their scores; and

for each of the displayed entities, providing a hyperlink to a report tree containing a plurality of hyperlinked reports, including at least one summary report providing a quantitative summary of data contributing to a reason the entity is included in the rank ordered listing;

wherein the report tree contains a plurality of reports comprising;

a suspect list of entities identified by the predictive model;

a breakdown report of each entity'"'"'s activity by a selected categorization of the entity'"'"'s activity, the breakdown report linked to the entity in the suspect list;

a distribution chart linked from the breakdown comparing activity of the entity to activity of the entity'"'"'s peers;

a first subset report linked to the breakdown report showing the breakdown o the entity'"'"'s activity by at least one of age or gender of other entities which interact with the entity;

a second subset report linked to the first distribution report showing the breakdown of the entity'"'"'s activity by at least one of age or gender of other entities which interact with the entity;

a tabular report, linked to at least one of the breakdown report, the distribution chart, the first subset report or the second subset report, showing activity of the entity with respect to a selected categorization of the entity'"'"'s activity;

a interacting entity summary report linked to the breakdown report showing a summary of activities of the entity with respect to each other entity which interacts with the entity;

a comparison report linked to at least one of the previous reports, comparing activity of the entity for at least one other entity with activity of the entity'"'"'s peers for the same at least one other entity; and

a report linked to at least one previous report, providing a listing of individual activities of an entity with respect to a selected categorization of the entity'"'"'s activities.

2. The method of claim 1, wherein the other entities are clients of the entity.

3. A computer implemented system for analyzing results of a predictive model applied to a data pertaining to a plurality of entities, the method comprising:

providing a predictive model for scoring the entities;

displaying a rank ordering at least some of the entities according to their scores, and for each of the displayed entities, providing a hyperlink to a report tree containing a plurality of hyperlinked reports, including at least one summary report providing a quantitative summary of data contributing to a reason the entity is included in the rank ordered listing;

wherein the report tree contains a plurality of reports comprising;

a suspect list report including a plurality of entities scored by the predictive model;

at least one entity-based report, linked to an individual entity in the suspect list, and providing a comparison of the individual entity'"'"'s activity with respect to activity of the entity'"'"'s peers;

at least one entity-subset report, linked an entity-based report, and providing a breakdown of the entity'"'"'s activity by a selected category;

at least one entity to other entity report, linked to an entity-based report, and providing a breakdown of an entity'"'"'s activity with respect to each other entity which interacts with the entity; and

at least one detail report, linked to at least one previous report, and providing a listing of activities that pertain to the report to which the detail report is linked.

4. The method of claim 3 wherein the predictive model is for identifying suspicious entities based on transactions associated with the entities.

5. The method of claim 3 wherein the entities include at least one entity that is derived from multiple entities that interact with each other.

6. The method of claim 3 wherein a reason for including an entity in the rank ordered listing is suspicious activity of the entity, and the report tree includes a summary report providing a summary of activity of the entity.

7. The method of claim 6, wherein an entity is included in the rank ordered listing if the entity'"'"'s activities are suspicious relative to the activities of the entity'"'"'s peers.

8. A computer implemented system for analyzing results of a predictive model applied to a data pertaining to a plurality of entities, the method comprising:

providing a predictive model for scoring the entities;

displaying a rank ordering at least some of the entities according to their scores, and for each of the displayed entities, providing a hyperlink to a report tree containing a plurality of hyperlinked reports, including at least one summary report providing a quantitative summary of data contributing to a reason the entity is included in the rank ordered listing;

wherein the entities are healthcare entities and the predictive model is for identifying suspicious healthcare entities from data including healthcare procedure reimbursement transactions associated with the entities; and

wherein the healthcare entities are selected from a set consisting of;

healthcare providers, patients, claims processors, doctors, hospitals, nursing facilities, practice groups, laboratories, and pharmacies, and interacting combinations of any of the foregoing entities.

9. The method of claim 8, wherein the summary report compares activity of the entity to activity of the entity'"'"'s'"'"' peers with respect to at least one of following:

a selected set of procedure code groups;

a selected set of diagnosis code groups;

a selected set of type of service codes; and

a selected set of place of service codes.

10. The method of claim 8, wherein the summary report compares activity of the entity to activity of the entity'"'"'s'"'"' peers with respect to an individual client of the entity.

11. The method of claim 8, wherein the summary report compares activity of the entity in each of a plurality of age groups of the entity'"'"'s clients to the activities of the entity'"'"'s peers in each of the age groups.

12. The method of claim 8, wherein the summary report compares activity of the entity in at least one month to activity of the entity'"'"'s peers in the at least one month.

13. The method of claim 12, wherein the summary report includes a hyperlink to another report that summarizes the entity'"'"'s activity in the at least one month with respect to at least one of procedure codes, diagnosis codes, place of service codes, and type of service codes.

14. The method of claim 8, wherein the summary report compares client consecutive visits of the entity for a selected period of time to client consecutive visits of the entity'"'"'s peers in the selected period of time.

15. The method of claim 8, wherein the summary report compares average dollars per claim for the entity with average dollars per claim for the entity'"'"'s peers.

16. The method of claim 15, wherein the summary report includes a hyperlink to a report providing a distribution of dollars per claim for the entity.

17. The method of claim 8, wherein the summary report compares per day activity of the entity with per day activity of the entity'"'"'s peers.

18. The method of claim 17, wherein the per activity is measured by at least one of the following:

dollars paid per client per day;

number of services per client per day;

number of clients per day;

dollars paid per day;

number of claims per day.

19. The method of claim 17, wherein the per activity is limited by at least one of the following:

procedure codes;

diagnosis codes;

type of services codes; and

place of service codes.

20. The method of claim 8, wherein the summary report compares the per client volume of activity of the entity with the entity'"'"'s peers.

21. The method of claim 20, wherein the per client volume of activity is measured by at least one of the following:

dollars paid per client;

number of clients;

number of services per client;

dollars paid to the entity per client;

number of services provided by the entity per client.

22. The method of claim 20, wherein the per client volume of activity is limited by at least one of the following:

procedure codes;

diagnosis codes;

type of services codes; and

place of service codes.

23. The method of claim 20, wherein the summary report includes a hyperlink to a report of activity volume for each of the entity'"'"'s clients, sorted according to a measure of the activity volume per client.

24. The method of claim 8, wherein the summary report compares the number of multiple entities seen per day by the entity'"'"'s clients to the number of multiple entities seen per day by the clients of the entity'"'"'s peers.

25. A computer implemented method of analyzing results of a predictive model applied to a data set pertaining to transactions of a plurality of entities, the method comprising:

executing a predictive model on the data set to select from the entities, a suspect list containing a plurality of suspects, the suspects rank ordered according to their predictive model scores, each suspect associated with a list of reasons generated by the predictive model for including the suspect in the suspect list, the reasons for each suspect rank ordered by their from a predetermined set of reasons;

for each reason, providing a hyperlink to a report tree comprising a plurality of predetermined hyperlinked reports, arranged by their hyperlinks to provide access from the reason in the suspect list to at least one summary report providing a summary analysis of data related to the reason and the suspect, at least one summary report hyperlinked directly or indirectly to at least one detail report containing a list of specific transactions which contribute to the inclusion of the suspect in the suspect list;

receiving a user input selecting for one a suspect from the suspect list a hyperlinked reason in the list of reasons associated with the suspect, and in response, generating from the report tree for the selected reason, a summary report providing the summary analysis of the transactions related to the selected reason and suspect; and

responsive to user input selecting a hyperlink to one of the detail reports, generating the selected detailed report from the transactions associated with suspect.