A large organization contacted System One to help them with their End User Support. The organization’s current support system was expensive, difficult to maintain and underutilized. One of the issues that the organization faced with their support team was with the fluctuation of ticket volume throughout the day. To alleviate any shortages on the high call volume days and still meet their Service Level Agreement (SLA) metrics, the client vendor adds more resources to the pool and assigns them to the appropriate shift, thereby increasing labor costs. This did address the issue of having enough agents to take the calls during the peak periods; however, during downtime, this left the resources underutilized. Ultimately this resulted in the organization having to outlay a significant amount of cost for resources without a return. The core of System One’s values are to take actions to utilize any available downtime to search for new opportunities and efficiencies.
System One analyzed the organization’s data from historical tickets and ran advanced analytics on that data. We then created an Artificial Intelligence (AI) model that would be able to understand that on Monday morning, a high number of users are calling because they cannot log in. At around 10:00am, there is a decline in ticket volume when users are in meetings are in mid-day focused work. The model also understood that on Friday’s at 11:30am, right before lunch, there was another surge before the weekend or on holidays. We used the trained model to predict the volume of calls based on historical data and determine the corresponding staff to schedule for the day!
The model that System One developed allowed the organization to “virtually” run the day to see how a schedule was changing during various times to match the demand of the tickets. The model was able to predict the optimum number of resources, as well as when to schedule them throughout the day. This significantly reduced overstaffing when demand was low. It provided insight on when to add staff and by how much, which then enabled the client to ultimately reach their SLA goals.
One of the biggest challenges for an organization is knowing how to schedule their technicians to optimize staffing. By using this simulation tool, a schedule was created to offset when people work, enabling the organization to maximize SLAs while keeping labor costs at their lowest. This in turn saves an average 15% of labor costs.