Case management virtual assistant to enable predictive outputs
A system, method, and computer-readable medium for performing a customer service interaction estimation operation, comprising: training a customer service interaction estimation system using a training dataset of cases to provide a trained predictive model; identifying current open cases via the customer service interaction system; applying the trained predictive model to the current open cases to identify low customer experience cases; generating an estimation output relating to the current open cases, the estimation output identifying an open case subset of cases having a high risk of high effort to resolve.
1. A computer-implementable method for performing a customer service interaction estimation operation, comprising:
training a customer service interaction estimation system using a training dataset of cases to provide a trained predictive model;
identifying current open cases via the customer service interaction system;
applying the trained predictive model to the current open cases to identify low customer experience (CE) cases;
generating an estimation output relating to the current open cases, the estimation output identifying an open case subset of cases having a high risk of high effort to resolve, the estimation output being used to generate an overall customer effort variable, the overall customer effort variable representing a customer effort score, the customer effort score comprising a numerical value representing a respective customer effort; and,
resampling the training dataset when training the customer service interaction system, the resampling comprising oversampling and undersampling, the oversampling randomly replicating minority instances to increase a population of minority instances, the undersampling randomly down sampling a minority class.
2. The method of claim 1 , further comprising:
providing the estimation output to a customer relationship management system; and,
performing preemptive corrective actions on the open case subset.
3. The method of claim 1 , wherein:
the training, applying and generating implement machine learning operations to generate the estimation output.
4. The method of claim 3 , wherein:
the machine learning operations comprise a decision tree machine learning model.
5. The method of claim 1 , wherein:
the training comprises using oversampling to randomly replicate minority instances.
6. The method of claim 1 , wherein:
the current open cases are identified from a live pool of active customer service cases.
7. A system comprising:
a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations and comprising instructions executable by the processor and configured for:
training a customer service interaction estimation system using a training dataset of cases to provide a trained predictive model;
identifying current open cases via the customer service interaction system;
applying the trained predictive model to the current open cases to identify low customer experience (CE) cases;
generating an estimation output relating to the current open cases, the estimation output identifying an open case subset of cases having a high risk of high effort to resolve, the estimation output being used to generate an overall customer effort variable, the overall customer effort variable representing a customer effort score, the customer effort score comprising a numerical value representing a respective customer effort; and,
resampling the training dataset when training the customer service interaction system, the resampling comprising oversampling and undersampling, the oversampling randomly replicating minority instances to increase a population of minority instances, the undersampling randomly down sampling a minority class.
8. The system of claim 7 , wherein the instructions executable by the processor are further configured for:
providing the estimation output to a customer relationship management system; and,
performing preemptive corrective actions on the open case subset.
9. The system of claim 7 , wherein:
the training, applying and generating implement machine learning operations to generate the estimation output.
10. The system of claim 9 , wherein:
the machine learning operations comprise a decision tree machine learning model.
11. The system of claim 7 , wherein:
the training comprises using oversampling to randomly replicate minority instances.
12. The system of claim 7 , wherein:
the current open cases are identified from a live pool of active customer service cases.
13. A non-transitory, computer-readable storage medium embodying computer program code, the computer program code comprising computer executable instructions configured for:
training a customer service interaction estimation system using a training dataset of cases to provide a trained predictive model;
identifying current open cases via the customer service interaction system;
applying the trained predictive model to the current open cases to identify low customer experience (CE) cases;
generating an estimation output relating to the current open cases, the estimation output identifying an open case subset of cases having a high risk of high effort to resolve, the estimation output being used to generate an overall customer effort variable, the overall customer effort variable representing a customer effort score, the customer effort score comprising a numerical value representing a respective customer effort; and,
resampling the training dataset when training the customer service interaction system, the resampling comprising oversampling and undersampling, the oversampling randomly replicating minority instances to increase a population of minority instances, the undersampling randomly down sampling a minority class.
14. The non-transitory, computer-readable storage medium of claim 13 , wherein the computer executable instructions are further configured for:
providing the estimation output to a customer relationship management system; and,
performing preemptive corrective actions on the open case subset.
15. The non-transitory, computer-readable storage medium of claim 13 , wherein:
the training, applying and generating implement machine learning operations to generate the estimation output.
16. The non-transitory, computer-readable storage medium of claim 15 , wherein:
the machine learning operations comprise a decision tree machine learning model.
17. The non-transitory, computer-readable storage medium of claim 13 , wherein:
the training comprises using oversampling to randomly replicate minority instances.
18. The non-transitory, computer-readable storage medium of claim 13 , wherein:
the current open cases are identified from a live pool of active customer service cases.
19. The non-transitory, computer-readable storage medium of claim 13 , wherein:
the computer executable instructions are deployable to a client system from a server system at a remote location.
20. The non-transitory, computer-readable storage medium of claim 13 , wherein:
the computer executable instructions are provided by a service provider to a user on an on-demand basis.