Apparatuses, methods, and computer program products for predictive determinations of causal change identification for service incidents

1. An apparatus for programmatically determining a predictive causal probability score data object associated with a service incident occurring within a federated service network, the apparatus comprising at least one processor and at least one memory, the at least one memory having computer-coded instructions therein, wherein the computer-coded instructions are configured to, in execution with the at least one processor, cause the apparatus to:

monitor the federated service network to identify a service incident data object associated with a service incident and a service incident time, the service incident data object comprising an impacted service identifier and one or more upstream service identifiers;

generate, using a predictive causal machine learning model, a predictive causal probability score data object based at least in part on the service incident time associated with the service incident data object, wherein (i) the predictive causal probability score data object describes two or more predictive causal probability scores, (ii) each predictive causal probability score is associated with a particular service change associated with the impacted service identifier or a particular upstream service change associated with each of the one or more upstream service identifiers, and (iii) each predictive causal probability score is indicative of a probability the corresponding particular service change or corresponding particular upstream service change is a cause contributor of the service incident described by the service incident data object;

cause generation of a causal change analysis interface on one or more client devices based on the predictive causal probability score data object, wherein the causal change analysis interface comprises:

a service incident element that describes at least one impacted service or upstream service,

a predictive causal probability score element listing each particular service change or upstream service change associated with each predictive causal probability score, and

a user interactable element rendered in association with each particular service change or upstream service change, wherein user interaction with the user interactable element causes reversal of the corresponding particular service change or upstream service change.

2. The apparatus of claim 1 , wherein generating the predictive causal probability score data object further comprises computer-coded instructions further configured to, in execution with the at least one processor, cause the apparatus to:

determine a time score value for each particular service change or particular upstream service change, wherein the time score value is based at least in part on the service incident time associated with the service incident data object and a service change time associated with the particular service change or particular upstream service change; and

generate, using the predictive causal machine learning model, a predictive causal probability score for each particular service change or particular upstream service change based at least in part on the corresponding time score value.

3. The apparatus of claim 1 , wherein generating the predictive causal probability score data object further comprises computer-coded instructions further configured to, in execution with the at least one processor, cause the apparatus to:

determine a risk assessment value for each particular service change or particular upstream service change, wherein the risk assessment value is based at least in part on one or more change risk factors associated with the corresponding impacted service identifier or upstream service identifier; and

generate, using the predictive causal machine learning model, a predictive causal probability score for each particular service change or particular upstream service change based at least in part on the corresponding risk assessment value.

4. The apparatus of claim 1 , wherein the computer-coded instructions are further configured to, in execution with the at least one processor, cause the apparatus to:

select one or more service changes or upstream service changes for which to generate the predictive causal probability score data object based at least in part on a change time window.

5. The apparatus of claim 1 , wherein generating the predictive causal probability score data object based at least in part on a service incident time associated with the service incident data object further comprises the computer-coded instructions further configured to, in execution with the at least one processor, cause the apparatus to:

extract, using a service incident analysis layer, one or more service incident analysis attributes; and

generate, using the predictive causal machine learning model, the predictive causal probability score data object based at least in part on the one or more service incident analysis attributes.

6. The apparatus of claim 1 , wherein the computer-coded instructions are further configured to, in execution with the at least one processor, cause the apparatus to:

determine one or more selected service changes or selected upstream service changes associated with predictive causal probability scores that satisfy one or more threshold predictive causal probability scores; and

generate the predictive causal probability score data object, wherein the predictive probability score data object includes only the one or more selected service changes or the selected upstream service changes that satisfy the one or more threshold predictive causal probability scores.

7. The apparatus of claim 1 , wherein the computer-coded instructions further configured to, in execution with the at least one processor, cause the apparatus to:

determine one or more selected service changes or selected upstream service changes associated with predictive causal probability scores that satisfy one or more threshold predictive causal probability scores; and

modify an impacted service or an impacted upstream service associated with the service change or upstream service change associated with a largest predictive causal probability score to a historical version.

8. The apparatus of claim 1 , wherein the computer-coded instructions further configured to, in execution with the at least one processor, cause the apparatus to:

determine one or more selected service changes or selected upstream service changes associated with predictive causal probability scores that satisfy one or more threshold predictive causal probability scores;

determine whether the one or more selected service changes or selected upstream service changes associated with a largest predictive causal probability score satisfies one or more certainty threshold scores; and

in an instance in which the one or more selected service changes or selected upstream service changes associated with the largest predictive causal probability score satisfies one or more certainty threshold scores, modify an impacted service or an impacted upstream service associated with the one or more selected service changes or selected upstream service changes associated with the largest predictive causal probability score to a historical version.

9. The apparatus of claim 1 , wherein the service incident element of the causal change analysis interface includes the service incident time and a type of incident.

10. The apparatus of claim 8 , wherein the predictive probability score data object comprises a ranked list of the one or more selected service changes or selected upstream service changes that are selected for inclusion in the ranked list based at least in part on the corresponding predictive causal probability score for each of the one or more selected service changes or selected upstream service changes, and wherein the ranked list is rendered to the causal change analysis interface as part of the predictive causal probability score element.

11. A computer-implemented method for programmatically determining a predictive causal probability score data object associated with a service incident occurring within a federated service network, the computer-implemented method comprising:

monitoring, using one or more processors, the federated service network to identify a service incident data object associated with a service incident and a service incident time, the service incident data object comprising an impacted service identifier and one or more upstream service identifiers;

generating, using the one or more processors and a predictive causal machine learning model, a predictive causal probability score data object based at least in part on the service incident time associated with the service incident data object, wherein (i) the predictive causal probability score data object describes two or more predictive causal probability scores, (ii) each predictive causal probability score is associated with a particular service change associated with the impacted service identifier or a particular upstream service change associated with each of the one or more upstream service identifiers, and (iii) each predictive causal probability score is indicative of a probability the corresponding particular service change or corresponding particular upstream service change is the cause of the service incident described by the service incident data object; and

cause generation of a causal change analysis interface on one or more client devices based on the predictive causal probability score data object, wherein the causal change analysis interface comprises:

a service incident element that describes at least one impacted service or upstream service,

a predictive causal probability score element listing each particular service change or upstream service change associated with each predictive causal probability score, and

a user interactable element rendered in association with each particular service change or upstream service change, wherein user interaction with the user interactable element causes reversal of the corresponding particular service change or upstream service change.

12. The computer-implemented method of claim 11 , wherein generating the predictive causal probability score data object further comprises:

determining, using the one or more processors, a time score value for each particular service change or particular upstream service change, wherein the time score value is based at least in part on the service incident time associated with the service incident data object and a service change time associated with the particular service change or particular upstream service change; and

generating, using the one or more processors and the predictive causal machine learning model, a predictive causal probability score for each particular service change or particular upstream service change based at least in part on the corresponding time score value.

13. The computer-implemented method of claim 11 , wherein generating the predictive causal probability score data object further comprises:

determining, using the one or more processors, a risk assessment value for each particular service change or particular upstream service change, wherein the risk assessment value is based at least in part on one or more change risk factors associated with the corresponding impacted service identifier or upstream service identifier; and

generating, using the one or more processors and the predictive causal machine learning model, a predictive causal probability score for each particular service change or particular upstream service change based at least in part on the corresponding risk assessment value.

14. The computer-implemented method of claim 11 , wherein the computer-implemented method further comprises:

selecting one or more selected service changes or selected upstream service changes for which to generate a predictive causal probability score based at least in part on a change time window.

15. The computer-implemented method of claim 11 , wherein generating the predictive causal probability score data object based at least in part on a service incident time associated with the service incident data object further comprises:

extracting, using the one or more processors and a service incident analysis layer, one or more service incident analysis attributes; and

generating, using the one or more processors and the predictive causal machine learning model, the predictive causal probability score data object based at least in part on the one or more service incident analysis attributes.

16. The computer-implemented method of claim 11 , wherein computer-implemented method further comprises:

determining, using the one or more processors, one or more selected service changes or selected upstream service changes associated with predictive causal probability scores that satisfy one or more threshold predictive causal probability scores; and

generating, using the one or more processors, the predictive probability score data object, wherein the predictive probability score data object includes only the one or more selected service changes or selected upstream service changes that satisfy the one or more threshold predictive causal probability scores.

17. The computer-implemented method of claim 11 , wherein computer-implemented method further comprises:

determining one or more selected service changes or selected upstream service changes associated with predictive causal probability scores that satisfy one or more threshold predictive causal probability scores;

determining whether the one or more selected service changes or selected upstream service changes associated with a largest predictive causal probability score satisfies one or more certainty threshold scores; and

in an instance in which the one or more selected service changes or selected upstream service changes associated with the largest predictive causal probability score satisfies one or more certainty threshold scores, modify an impacted service or an impacted upstream service associated with the one or more selected service changes or selected upstream service changes associated with the largest predictive causal probability score to a historical version.

18. The computer-implemented method of claim 11 , wherein the service incident element of the causal change analysis interface includes the service incident time and a type of incident.

19. The computer-implemented method of claim 11 , wherein the predictive probability score data object comprises a ranked list of one or more selected service changes or selected upstream service changes that are selected for inclusion in the ranked list based at least in part on the corresponding predictive causal probability score for each of the one or more selected service changes or selected upstream service changes, and wherein the ranked list is rendered to the causal change analysis interface as part of the predictive causal probability score element.