Abstract: Embodiments of the present disclosure provide systems and methods for generating a plurality of forecasts for a future time interval using a plurality of models and/or algorithms in order to assess the performance of each model. An example computer-implemented method can comprise generating a fitness function visualization corresponding with determined quantitative measures of forecast quality for each of the plurality of models and/or algorithms.

Abstract: A method for providing benchmark-plans to a customer based on benchmark information, comprising receiving a customer-defined service goal and a demand forecast for the customer; generating, with a planner, a plan for achieving the customer-defined service goal based on the demand forecast; determining a benchmark category from a plurality of benchmark categories that the customer belongs to based on at least an industry of the customer, wherein the benchmark category defines a plurality of other customer-defined service goals for other customers participating in at least the industry as the customer; determining benchmark service goals based on the determined benchmark category; executing the planner for each of the benchmark service goals thereby generating benchmark-plans for the demand forecast for the customer; and outputting, to the customer, the plan and the benchmark-plans, wherein the benchmark-plans are different from the plan.

Abstract: The present disclosure describes methods and systems for selecting the forecasting algorithm to use for a prediction based on motifs. A motif is a pattern of interval values that is found to repeat in time series data. Time series data that includes historical demand data (e.g., average communication volume) for an entity at various time intervals in the past is received. The time series data is processed to identify motifs. For each identified motif, the forecasting algorithm that best predicts the historical demand data for time intervals associated with the motif is determined. Later, when the entity desires to receive a forecast for a future time interval, the motif associated with the future time interval is determined. The forecasting algorithm determined to best predict demand for the determined motif is then used to predict the demand for the future time interval.

Abstract: Methods and systems for selecting a forecasting algorithm to use for a forecast for a time interval are provided. A class is a series of time intervals that is selected by an entity from time series data that relates to external data or is a series of time intervals from the time series data that corresponds to a motif. The time series data is processed by a computer to identify motifs, and classes are generated based on each identified motif. A user may further identify one or more classes in the time series data. For each class, the forecasting algorithm that best predicts the historical demand data for time intervals associated with the class is determined. Later, when the entity desires to receive a forecast for a future time interval, the class associated with the future time interval is determined. The forecasting algorithm determined to best predict demand for the determined class is then used.

Abstract: In an entity such as a call center, back office, or retail operation, external event data is recorded along with call volume information for a plurality of time intervals. Based on the recorded event data and call volume for the plurality of intervals, a model is trained to predict call (or other communication) volume for a specified time interval using the external event data. The external event data may include data about one or more events that may affect the demand received by the entity. When the predicted call volume is significantly above or below what would be predicted for the entity using historical data alone, an indicator may be displayed to a user or administrator that identifies the external event that is responsible for the lower or higher prediction. The call volume prediction may be used to schedule one or more agents (or other employees) to work during the specified time interval.

Abstract: In an entity such as a call center, back office, or retail operation, external event data is recorded along with call volume information for a plurality of time intervals. Based on the recorded event data and call volume for the plurality of intervals, a model is trained to predict call (or other communication) volume for a specified time interval using the external event data. The external event data may include data about one or more events that may affect the demand received by the entity. When the predicted call volume is significantly above or below what would be predicted for the entity using historical data alone, an indicator may be displayed to a user or administrator that identifies the external event that is responsible for the lower or higher prediction. The call volume prediction may be used to schedule one or more agents (or other employees) to work during the specified time interval.

Abstract: Matching deployable resources with available tasks based on personal information obtained from wearable devices is disclosed. A processor-based controller receives permission from each of a plurality of deployable resources to receive personal information from the respective deployable resource. The controller next automatically receives personal information from each of the plurality of deployable resources via the wearable devices. The personal information is based on information determined by the respective wearable device while the wearable device is being worn by the respective deployable resource. The controller automatically compares the personal information received from one or more of the deployable resources to a selection criterion associated with a task. Based on the comparing, the controller selects one or more of the deployable resources, and notifies each of the selected deployable resources to request assistance with respect to the task.

Abstract: Authorizing deployable resources based on personal information obtained from wearable devices is disclosed. A processor-based controller automatically receives personal information about a deployable resource via a wearable device configured to be worn by the deployable resource. The personal information is based on information determined by the wearable device while the wearable device is being worn by the deployable resource. The controller automatically compares the personal information of the deployable resource to a criterion associated with a task and automatically determines, based on the comparing, whether the deployable resource is permitted to proceed with the task. If the controller determines that the deployable resource is permitted to proceed with the task, the controller permits the deployable resource to proceed with the task.

Abstract: Selecting deployable resources based on personal information obtained from wearable devices is disclosed. A processor-based controller automatically determines a contact load parameter and a contact load threshold for a contact center. If the contact load parameter for the contact center exceeds the contact load threshold, the controller automatically selects one or more deployable resources from a resource pool by receiving personal information about each of the deployable resources in the resource pool via a respective wearable device configured to be worn by each deployable resource and comparing the personal information based on a selection criterion for each deployable resource. The controller selects one or more deployable resources based on the comparisons. The selected deployable resources are then notified to request their assistance with respect to the contact center.

Abstract: Authorizing deployable resources based on personal information obtained from wearable devices is disclosed. A processor-based controller automatically receives personal information about a deployable resource via a wearable device configured to be worn by the deployable resource. The personal information is based on information determined by the wearable device while the wearable device is being worn by the deployable resource. The controller automatically compares the personal information of the deployable resource to a criterion associated with a task and automatically determines, based on the comparing, whether the deployable resource is permitted to proceed with the task. If the controller determines that the deployable resource is permitted to proceed with the task, the controller permits the deployable resource to proceed with the task.

Abstract: Matching deployable resources with available tasks based on personal information obtained from wearable devices is disclosed. A processor-based controller receives permission from each of a plurality of deployable resources to receive personal information from the respective deployable resource. The controller next automatically receives personal information from each of the plurality of deployable resources via the wearable devices. The personal information is based on information determined by the respective wearable device while the wearable device is being worn by the respective deployable resource. The controller automatically compares the personal information received from one or more of the deployable resources to a selection criterion associated with a task. Based on the comparing, the controller selects one or more of the deployable resources, and notifies each of the selected deployable resources to request assistance with respect to the task.

Abstract: An agent at a contact center uses a soft phone embedded in the agent's desktop to converse with a customer, to set the agent's Automatic Call Distribution (“ACD”) state, and to control the phone's call control state. Computer Telephony Integration (“CTI”) technology is used in many ways at the contact center, including for accessing CTI data and executing CTI methods. CTI data can include information about the calling number, called number, caller entered digits, and the queue the call came from. CTI methods can include call control operations such as answering a call, making a call, and transferring a call. In addition, CTI methods can also include ACD specific operations, such as setting an agent's state and querying the state of a queue of customers. A web browser is also embedded in the agent's desktop, and one or more web-based applications are integrated into the web browser. These applications may be web-based enterprise applications or other web-based applications such as available over the internet.