Abstract: Systems, methods, and computer program products for generating job value predictions by a trained model for a tenant include receiving live data associated with a tenant, where the live data includes information associated with a job to be performed by the tenant. A trained model associated with the tenant is retrieved, where the trained model is configured to generate a job value prediction for the job to be performed. The live data is preprocessed to obtain a set of features associated with the job, the set of features consumable by the trained model, and the trained model is applied to the set of features to generate the job value prediction for the job to be performed by the tenant.

Abstract: Aspects of the present disclosure involve systems, methods, computer program products, and the like, for scheduling and assigning work to a plurality of workers or service technicians. Data identifying jobs, timeframes that respective jobs should be performed, and job locations may be compared to times when workers are available to work. Each of the workers may be assigned particular jobs to begin during specific timeframes. These assignments may be based on information that identifies time slots when each worker is available to work, an estimated amount of time that particular jobs should take, skills of particular workers, and estimated travel times between jobs. After specific workers have been identified to work on specific jobs, a scheduling computer may send messages to computing devices of respective workers to schedule or reschedule work. These messages may identify job locations and timeframes that each job should be performed or begun.

Abstract: Aspects of the present disclosure involve systems, methods, computer program products, and the like, for generating technician dispatching schedules. The dispatching schedule can be generated on demand or on-the-fly based on a plurality of complex factors such as job requirements, technician skill, technician location, job value, technician sales ability, technician location, future job locations, overall availability of other technicians, or other factors. A graph may be used to generate job assignments for the dispatching schedule. Nodes of the graph may respectively represent timeslots and jobs to specific technicians. Methods and apparatus consistent with the present disclosure may be used to assign specific jobs to specific technicians and to specific timeslots, thereby, increasing efficiency and profits of a service company.

Abstract: Systems, methods, and computer program products for generating job value predictions by a trained model for a tenant include receiving live data associated with a tenant, where the live data includes information associated with a job to be performed by the tenant. A trained model associated with the tenant is retrieved, where the trained model is configured to generate a job value prediction for the job to be performed. The live data is preprocessed to obtain a set of features associated with the job, the set of features consumable by the trained model, and the trained model is applied to the set of features to generate the job value prediction for the job to be performed by the tenant.