Abstract: Embodiments are directed to improving performance criterion in a control session. Information associated with an agent may be obtained. A predicted expenditure may be generated based on the information and a performance model. The predicted expenditure may be transformed into specific-units amounts of multiple resource types based on the characteristics information. Each specific-units amount may be transformed into a normalized-units amount based on one or more normalized-units amounts of one or more other resource types. An instruction may be provided to the agent based on the normalized-units amounts. Metrics based on monitoring the agent may be obtained. One or more portions of the metrics may be compared to one or more outputs of the performance model. One or more outputs of the model may be modified based on the comparison to increase a correlation between one or more outputs and the metrics.

Abstract: Embodiments are directed to improving performance criterion in a control session. Information associated with an agent may be obtained. A predicted expenditure may be generated based on the information and a performance model. The predicted expenditure may be transformed into specific-units amounts of multiple resource types based on the characteristics information. Each specific-units amount may be transformed into a normalized-units amount based on one or more normalized-units amounts of one or more other resource types. An instruction may be provided to the agent based on the normalized-units amounts. Metrics based on monitoring the agent may be obtained. One or more portions of the metrics may be compared to one or more outputs of the performance model. One or more outputs of the model may be modified based on the comparison to increase a correlation between one or more outputs and the metrics.

Abstract: Embodiments are directed to improving performance criterion in a control session. Information associated with an agent may be obtained. A predicted expenditure may be generated based on the information and a performance model. The predicted expenditure may be transformed into specific-units amounts of multiple resource types based on the characteristics information. Each specific-units amount may be transformed into a normalized-units amount based on one or more normalized-units amounts of one or more other resource types. An instruction may be provided to the agent based on the normalized-units amounts. Metrics based on monitoring the agent may be obtained. One or more portions of the metrics may be compared to one or more outputs of the performance model. One or more outputs of the model may be modified based on the comparison to increase a correlation between one or more outputs and the metrics.