Claims:1. A processor implemented method, comprising:
obtaining one or more of units, product backlog items (PBIs), and events in said PBIs for a first sprint;
modelling said one or more of units, PBIs, and events in said PBIs in an inverse Bayesian Belief Network to generate a Probabilistic Graphical Model, wherein said one or more of units, PBIs, and events in said PBIs are modelled based on dependencies across said one or more of units, PBIs, and events in said PBIs;
generating an application knowledge by applying a machine learning technique on said probabilistic graphical model;
obtaining a PBI pertaining to a second sprint; and
generating, using said baseline application knowledge, one or more test cases for at least one application under test (AUT) based on said PBI pertaining to said second sprint.

2. The processor implemented method of claim 1, further comprising executing said one or more test cases to identify one or more defects in a third sprint, and performing a defect root cause analysis on said one or more defects through said Probabilistic Graphical Model.

3. The processor implemented method of claim 2, further comprising mapping, by using said inverse Bayesian Belief Network, said one or more defects to said one or more of units, PBIs, and events in said PBIs in said Probabilistic Graphical Model to generate an updated Probabilistic Graphical Model, said updated Probabilistic Graphical Model comprising one or more nodes and said one or more defects.

4. The processor implemented method of claim 3, further comprising
assigning, using an Arpeggio module, an influencing parameter to each of said one or more nodes in said updated Probabilistic Graphical Model; and
computing a dependency factor for each defect from the one or more defects, wherein the dependency factor is indicative of each defect that is being dependent on another defect.

5. The processor implemented method of claim 4, further comprising predicting, using an Artificial Neural Network, one or more defect friendly paths in said Probabilistic Graphical Model based on at least one of said influencing parameter and said dependency factor.

6. A system comprising:
a memory storing instructions;
one or more communication interfaces;
a hardware processor coupled to said memory through said one or more communication interfaces, wherein said hardware processor is configured to:
obtain one or more of units, product backlog items (PBIs), and events in said PBIs for a first sprint; and
an inverse Bayesian Belief Network that is configured to model said one or more of units, PBIs, and events in said PBIs in an inverse Bayesian Belief Network to generate a Probabilistic Graphical Model, wherein said one or more of units, PBIs, and events in said PBIs are modelled based on dependencies across said one or more of units, PBIs, and events in said PBIs,
wherein said hardware processor is further configured by said instructions to:
generate an application knowledge by applying a machine learning technique on said probabilistic graphical model,
obtain a PBI pertaining to a second sprint, and
generate, using said baseline application knowledge, one or more test cases for at least one application under test (AUT) based on said PBI pertaining to said second sprint.

7. The system of claim 6, wherein said hardware processor is further configured by said instructions to:
execute said one or more test cases to identify one or more defects in a third sprint, and
perform a defect root cause analysis on said one or more defects through said Probabilistic Graphical Model.

8. The system of claim 7, wherein said inverse Bayesian Belief Network is further configured to map said one or more defects to said one or more of units, PBIs, and events in said PBIs in said Probabilistic Graphical Model to generate an updated Probabilistic Graphical Model, said updated Probabilistic Graphical Model comprising one or more nodes and said one or more defects.

9. The system of claim 8, further comprising an Arpeggio module that is configured to assign an influencing parameter to each of said one or more nodes in said updated Probabilistic Graphical Model, and compute a dependency factor for each defect from the one or more defects, wherein the dependency factor is indicative of each defect that is being dependent on another defect.

10. The system of claim 9, further comprising an Artificial Neural Network that is configured to predict one or more defect friendly paths in said Probabilistic Graphical Model based on at least one of said influencing parameter and said dependency factor , Description:As Attached