EVENT PREDICTION SYSTEM AND METHOD

• US 20170154276A1
• Filed: 07/19/2016
• Published: 06/01/2017
• Est. Priority Date: 11/27/2015
• Status: Active Grant

• Current Assignee: TATA Consultancy Services Limited (Tata Sons Pvt Ltd.)
• Original Assignee: TATA Consultancy Services Limited (Tata Sons Pvt Ltd.)
• Inventors: SRIVASTAVA, Rajiv Radheyshyam, PAWAR, Sachin, PALSHIKAR, Girish Keshav
• Granted Patent: US 11,195,113 B2
• Time in Patent Office: Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 10/1053 Employment or hiring
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities

Abstract

Event prediction system and method includes gathering data corresponding to multiple entities to derive multiple entity profiles. Next, a first subset of entity profiles is identified from the multiple entity profiles generated. The identification is done on the basis of characteristics associated with the entities. Subsequent to identification of the first subset of the entity profiles, a second subset of entity profiles is shortlisted. Here, the second subset of entity profiles shows highest probability of occurrence of the event. Further, a determination of a factor that may lead to occurrence of the event is done.

Claims

1. A processor-implemented method for determining factors contributing to occurrence of an event, the method comprising:

gathering, via one or more hardware processors, data corresponding to a plurality of entities to derive a plurality of entity profiles, wherein the data represents characteristics associated with entities and each entity from amongst the plurality of entities is associated with a profile from amongst the plurality of entity profiles;

identifying, via one or more hardware processors, a first subset of entity profiles from amongst the plurality of entity profiles based on analysis of a first set of characteristics and a predetermined limit, wherein the first set of characteristics is chosen from amongst the characteristics associated with the entities;

predicting, via one or more hardware processors, a second subset of entity profiles from amongst the first subset of entity profiles based on comparison of the first subset of entity profiles with a preliminary subset of entity profiles, wherein the second subset of entity profiles are demonstrative of probable occurrence of an event; and

determining, via one or more hardware processors, for each entity profile within the second subset of entity profiles, at least one factor contributing to the occurrence of the event.

2. The method of claim 1, wherein the method further comprises generating a causal report based on the at least one factor.

3. The method of claim 1, wherein the predetermined limit is received from a user.

4. The method of claim 3, wherein the predetermined limit is a predetermined threshold value.

5. The method of claim 3, wherein the predetermined limit is a predetermined range of values.

6. The method of claim 1, wherein the preliminary subset of entity profiles is a subset of historic entity profiles stored in a repository.

7. The method of claim 1, wherein the preliminary subset of entity profiles is a subset of entity profiles demonstrating characteristics contrasting to the characteristics of the first subset of entity profiles.

8. The method of claim 6, wherein the historic entity profile are demonstrative of occurrence of the event in past.

9. The method of claim 1, wherein the determining for each entity profile within the second subset of entity profiles, at least one factor contributing to the occurrence of the event comprising:

comparing, the characteristics of the second subset of entity profiles with the characteristics of the contrasting entity profiles; and

identifying, at least one dissimilar characteristics after the comparison as the at least one factor contributing to the occurrence of the event.

10. The method of claim 2, further comprising generating a prevention plan for the occurrence of the event based on the causal report.

11. The method of claim 10, wherein the generation of the prevention plan for the second subset of entities comprises:

analyzing the factors in the causal report to identify similar causal factors for each entity profile in the second subset; and

preparing the prevention plan for the occurrence of the event, wherein the prevention plan is a list of corrective measures to be used to prevent the occurrence of the event.

12. An event prediction system associated with the event, comprises:

a processor having,

a profile creation module, to

gather data corresponding to a plurality of entities to derive a plurality of entity profiles, wherein the data represents characteristics associated with entities and each entity from amongst the plurality of entities is associated with a profile from amongst the plurality of entity profiles;

a discovery module, to

identify a first subset of entity profiles from amongst the plurality of entity profiles based on analysis of a first set of characteristics and a predetermined limit, wherein the first set of characteristics is chosen from amongst the characteristics associated with the entities;

a predictive analysis module, to

predict a second subset of entity profiles from amongst the first subset of entity profiles based on comparison of the first subset of entity profiles with repository preliminary subset of entity profiles, wherein the second subset of entity profiles are demonstrative of probable occurrence of an event; and

a causal analysis module, to

determine, for each entity profile within the second subset of entity profiles, at least one factor contributing to the occurrence of the event.

13. The system of claim 12, further comprising a preventive analysis module to generate a prevention plan for the occurrence of the event, wherein the prevention plan is based on a causal report, wherein the causal report consists of at least one factor contributing to the occurrence of the event.

14. The system of claim 12, wherein the preliminary subset of entity profiles is a subset of historic entity profiles stored in a repository.

15. The system of claim 12, wherein the preliminary subset of entity profiles is a subset of entity profiles demonstrating characteristics contrasting to the characteristics of the first subset of entity profiles.

16. The system of claim 13, wherein the generation of the prevention plan comprises:

analyzing the factors in the causal report to identify similar causal factors for each entity profile in the second subset; and

preparing the prevention plan for the occurrence of the event, wherein the prevention plan is a list of corrective measures to be used to prevent the occurrence of the event.

17. A non-transitory computer-readable medium having embodied thereon a computer program for executing a method for determining factors contributing to occurrence of an event, the method comprising:

gathering, via one or more hardware processors, data corresponding to a plurality of entities to derive a plurality of entity profiles, wherein the data represents characteristics associated with entities and each entity from amongst the plurality of entities is associated with a profile from amongst the plurality of entity profiles;

identifying, via one or more hardware processors, a first subset of entity profiles from amongst the plurality of entity profiles based on analysis of a first set of characteristics and a predetermined limit, wherein the first set of characteristics is chosen from amongst the characteristics associated with the entities;

predicting, via one or more hardware processors, second subset of entity profiles from amongst the first subset of entity profiles based on comparison of the first subset of entity profiles with repository preliminary subset of entity profiles, wherein the second subset of entity profiles are demonstrative of probable occurrence of an event; and

determining, via one or more hardware processors, for each entity profile within the second subset of entity profiles, at least one factor contributing to the occurrence of the event.

18. The non-transitory computer-readable medium of claim 17, wherein the method further comprises generating a causal report based on the at least one factor.

19. The non-transitory computer-readable medium of claim 17, further comprises generating a prevention plan for the occurrence of the event based on the causal report.

20. The non-transitory computer-readable medium of claim 19, wherein the generation of the prevention plan for the second subset of entities comprises:

analyzing the factors in the causal report to identify similar causal factors for each entity profile in the second subset; and

preparing the prevention plan for the occurrence of the event, wherein the prevention plan is a list of corrective measures to be used to prevent the occurrence of the event.