Claims:We claim:
1. A method for predicting a success rate of a project in real-time, comprising:
initiating, by a prediction system, a natural language conversation with a stakeholder associated with a project to determine one or more features relevant for the stakeholder, wherein the one or more features are determined by performing a Bayesian network analysis of one or more properties associated with the project.
creating, by the prediction system, a relationship structure, comprising the one or more features, based on natural language processing of the natural language conversation, wherein each of the one or more features are assigned a score;
creating, by the prediction system, a prediction model with relative weightage values to each of the one or more relevant features based on the assigned score, wherein the prediction model is trained based on a historic data associated with the project; and
predicting, by the prediction system, a success rate of the project based on the trained prediction model and a current state of the project.

2. The method as claimed in claim 1, further comprising determining factors affecting the success rate of the project.

3. The method as claimed in claim 1, wherein the one or more features comprises one or more parameters associated with the project and priority details of the one or more parameters.

4. The method as claimed in claim 3, wherein the score of each of the one or more features is based on the relationship between the one or more parameters of the corresponding one or more features.

5. The method as claimed in claim 1, wherein the prediction model is a logistic regression model.

6. A prediction system for predicting a success rate of a project in real-time, comprises:
a processor; and
a memory communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which, on execution, cause the processor to:
initiate a natural language conversation with a stakeholder associated with a project to determine one or more features relevant for the stakeholder, wherein the one or more features are determined by performing a Bayesian network analysis of one or more properties associated with the project;
create a relationship structure, comprising the one or more features, based on natural language processing of the natural language conversation, wherein each of the one or more features are assigned a score;
create a prediction model with relative weightage values to each of the one or more relevant features based on the assigned score, wherein the prediction model is trained based on a historic data associated with the project; and
predict a success rate of the project based on the trained prediction model and a current state of the project.

7. The prediction system as claimed in claim 6, wherein the processor is further configured to determine factors affecting the success rate of the project.

8. The prediction system as claimed in claim 6, wherein the one or more features comprises one or more parameters associated with the project and priority details of the one or more parameters.

9. The prediction system as claimed in claim 8, wherein the score of each of the one or more features is based on the relationship between the one or more parameters of the corresponding one or more features.

10. The prediction system as claimed in claim 6, wherein the prediction model is a logistic regression model.

Dated this 21st day of December, 2016

R Ramya Rao
Of K&S Partners
Agent for the Applicant
, Description:TECHNICAL FIELD
The present subject matter is related in general to the field of project management, more particularly, but not exclusively to a method and system for predicting success rate of a project in real-time.