Systems and methods for repurposing paid time off
The present disclosure relates generally to utilizing paid time off. In one example, the systems and methods described herein may provide an infrastructure to repurpose paid time off into other uses, such as cash, travel, bill payments, and the like.
1. A method comprising:
obtaining historical data, wherein the historical data includes historical information corresponding to workforce usage of paid time off benefits and to processing of workforce requests to use the paid time off benefits, and wherein the historical data is associated with a workforce;
identifying one or more insights corresponding to the workforce usage of the paid time off benefits and workforce performance, wherein the one or more insights are generated using a machine learning algorithm;
generating paid time off data, wherein the paid time off data is associated with the workforce usage of the paid time off benefits, and wherein the paid time off data indicates dates corresponding to one or more periods of time during which the workforce usage of the paid time off benefits and workforce demand is predicted to be elevated;
generating one or more recommendations for policies extendable to the workforce, wherein the policies correspond to workforce quality of life, and wherein the one or more recommendations are generated using the machine learning algorithm based on the one or more insights;
providing the paid time off data and the one or more recommendations for the policies extendable to the workforce; and
updating the machine learning algorithm, wherein the machine learning algorithm is updated using new workforce requests to use the paid time off benefits, the paid time off data, and the one or more recommendations.
2. The method of claim 1 , further comprising:
identifying the workforce requests to use the paid time off benefits; and
updating the paid time off data to indicate the workforce requests to use the paid time off benefits.
3. The method of claim 1 , further comprising:
receiving a request to use the paid time off benefits;
evaluating the request to identify an intent for using the paid time off benefits;
determining a likelihood that the request will be approved, wherein the likelihood is determined using the request and the intent as input to the machine learning algorithm; and
providing a response to the request, wherein the response indicates the likelihood.
4. The method of claim 1 , further comprising:
identifying biases corresponding to the processing of the workforce requests to use the paid time off benefits, wherein the biases are identified using the machine learning algorithm; and
updating the paid time off data to indicate the biases.
5. The method of claim 1 , further comprising:
identifying one or more blackout dates, wherein the one or more blackout dates correspond to dates during which the paid time off benefits cannot be used; and
updating the paid time off data to indicate the one or more blackout dates.
6. The method of claim 1 , further comprising:
identifying one or more approved requests to use the paid time off benefits, wherein the one or more approved requests correspond to a set of dates, and wherein the set of dates are associated with a level of the workforce usage of the paid time off benefits;
obtaining a new level of the workforce usage of the paid time off benefits, wherein the new level is determined based on the level and the one or more approved requests; and
dynamically updating the paid time off data based on the new level.
7. The method of claim 1 , wherein identifying the one or more insights includes:
identifying an impact associated with the workforce usage of paid time off benefits; and
generating a confidence score corresponding to the impact, wherein when the confidence score satisfies a confidence threshold, the impact is used to generate the one or more insights.
8. A system, including:
one or more processors; and
memory including instructions that, as a result of being executed by the one or more processors, cause the system to:
obtain historical data, wherein the historical data includes historical information corresponding to workforce usage of paid time off benefits and to processing of workforce requests to use the paid time off benefits, and wherein the historical data is associated with a workforce;
identify one or more insights corresponding to the workforce usage of the paid time off benefits and workforce performance, wherein the one or more insights are generated using a machine learning algorithm;
generate paid time off data, wherein the paid time off data is associated with the workforce usage of the paid time off benefits, and wherein the paid time off data indicates dates corresponding to one or more periods of time during which the workforce usage of the paid time off benefits and workforce demand is predicted to be elevated;
generate one or more recommendations for policies extendable to the workforce, wherein the policies correspond to workforce quality of life, and wherein the one or more recommendations are generated using the machine learning algorithm based on the one or more insights;
provide the paid time off data and the one or more recommendations for the policies extendable to the workforce; and
update the machine learning algorithm, wherein the machine learning algorithm is updated using new workforce requests to use the paid time off benefits, the paid time off data, and the one or more recommendations.
9. The system of claim 8 , wherein the instructions further cause the system to:
identify the workforce requests to use the paid time off benefits; and
update the paid time off data to indicate the workforce requests to use the paid time off benefits.
10. The system of claim 8 , wherein the instructions further cause the system to:
receive a request to use the paid time off benefits;
evaluate the request to identify an intent for using the paid time off benefits;
determine a likelihood that the request will be approved, wherein the likelihood is determined using the request and the intent as input to the machine learning algorithm; and
provide a response to the request, wherein the response indicates the likelihood.
11. The system of claim 8 , wherein the instructions further cause the system to:
identify biases corresponding to the processing of the workforce requests to use the paid time off benefits, wherein the biases are identified using the machine learning algorithm; and
update the paid time off data to indicate the biases.
12. The system of claim 8 , wherein the instructions further cause the system to:
identify one or more blackout dates, wherein the one or more blackout dates correspond to dates during which the paid time off benefits cannot be used; and
update the paid time off data to indicate the one or more blackout dates.
13. The system of claim 8 , wherein the instructions further cause the system to:
identify one or more approved requests to use the paid time off benefits, wherein the one or more approved requests correspond to a set of dates, and wherein the set of dates are associated with a level of the workforce usage of the paid time off benefits;
obtain a new level of the workforce usage of the paid time off benefits, wherein the new level is determined based on the level and the one or more approved requests; and
dynamically update the paid time off data based on the new level.
14. The system of claim 8 , wherein the instructions that cause the system to identify the one or more insights further cause the system to:
identify an impact associated with the workforce usage of paid time off benefits; and
generate a confidence score corresponding to the impact, wherein when the confidence score satisfies a confidence threshold, the impact is used to generate the one or more insights.
15. A non-transitory computer-readable storage medium storing thereon executable instructions that, as a result of being executed by one or more processors of a computer system, cause the computer system to:
obtain historical data, wherein the historical data includes historical information corresponding to workforce usage of paid time off benefits and to processing of workforce requests to use the paid time off benefits, and wherein the historical data is associated with a workforce;
identifying one or more insights corresponding to the workforce usage of the paid time off benefits and workforce performance, wherein the one or more insights are generated using a machine learning algorithm;
generate paid time off data, wherein the paid time off data is associated with the workforce usage of the paid time off benefits, and wherein the paid time off data indicates dates corresponding to one or more periods of time during which the workforce usage of the paid time off benefits and workforce demand is predicted to be elevated;
generate one or more recommendations for policies extendable to the workforce, wherein the policies correspond to workforce quality of life, and wherein the one or more recommendations are generated using the machine learning algorithm based on the one or more insights;
provide the paid time off data and the one or more recommendations for the policies extendable to the workforce; and
update the machine learning algorithm, wherein the machine learning algorithm is updated using new workforce requests to use the paid time off benefits, the paid time off data, and the one or more recommendations.
16. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions further cause the computer system to:
identify the workforce requests to use the paid time off benefits; and
update the paid time off data to indicate the workforce requests to use the paid time off benefits.
17. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions further cause the computer system to:
receive a request to use the paid time off benefits;
evaluate the request to identify an intent for using the paid time off benefits;
determine a likelihood that the request will be approved, wherein the likelihood is determined using the request and the intent as input to the machine learning algorithm; and
provide a response to the request, wherein the response indicates the likelihood.
18. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions further cause the computer system to:
identify biases corresponding to the processing of the workforce requests to use the paid time off benefits, wherein the biases are identified using the machine learning algorithm; and
update the paid time off data to indicate the biases.
19. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions further cause the computer system to:
identify one or more blackout dates, wherein the one or more blackout dates correspond to dates during which the paid time off benefits cannot be used; and
update the paid time off data to indicate the one or more blackout dates.
20. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions further cause the computer system to:
identify one or more approved requests to use the paid time off benefits, wherein the one or more approved requests correspond to a set of dates, and wherein the set of dates are associated with a level of the workforce usage of the paid time off benefits;
obtain a new level of the workforce usage of the paid time off benefits, wherein the new level is determined based on the level and the one or more approved requests; and
dynamically update the paid time off data based on the new level.
21. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions that cause the computer system to identify the one or more insights further cause the computer system to:
identify an impact associated with the workforce usage of paid time off benefits; and
generate a confidence score corresponding to the impact, wherein when the confidence score satisfies a confidence threshold, the impact is used to generate the one or more insights.