APPLYING MACHINE LEARNING TO DYNAMICALLY SCALE COMPUTING RESOURCES TO SATISFY A SERVICE LEVEL AGREEMENT (SLA)

Some examples include a service to receive a job request that includes a job, a priority of the job, and a callback that identifies an application to execute the job. The application may be hosted by a particular virtual machine of a plurality of virtual machines being executed in a cloud hosting facility. The service may add the job request to a queue and determine, using a machine learning algorithm, a risk score associated with the job. Based at least in part on the risk score, the service may send a provisioning request to the cloud hosting facility to provision one or more additional virtual machines. After determining that the application has completed executing the job, the service may send a de-provisioning request to the cloud hosting facility to de-provision at least one virtual machine of the one or more additional virtual machines.