Systems and methods for scheduling tasks

A system, the system comprising:

• a database system implemented using a server system including at least one processor, the database system configurable to cause:
• processing a request for a first service associated with a first location, the request being received from a first client device;
• obtaining, from one or more database records of a database, historical information pertaining to one or more services that have been completed, the historical information indicating, for at least one service, a corresponding location, a completion time, and an identity of a field professional that performed the service;
• generating or updating a machine learning model based, at least in part, on the historical information;
• generating, using the machine learning model, a first likelihood value indicating a first likelihood that a first field professional will complete the first service at the first location in a single on-site visit based, at least in part, on a set of attributes of the first service;
• generating, by the one or more servers using the machine learning model, a second likelihood value indicating a second likelihood that a second field professional will complete the first service at the first location in a single on-site visit based, at least in part, on the set of attributes of the first service;
• comparing the first likelihood value and the second likelihood value;
• determining whether the first likelihood value is greater than the second likelihood value;
• assigning the first field professional or the second field professional to perform the first service based, at least in part, on a result of determining whether the first likelihood value is greater than the second likelihood value;
• and
• updating the machine learning model based, at least in part, on information pertaining to the first service after assigning the first field professional to perform the first service.

A computer program product comprising computer-readable program code capable of being executed by one or more processors when retrieved from a non-transitory computer-readable medium, the program code comprising computer-readable instructions configurable to cause:

• processing a request for a first service associated with a first location, the request being received from a first client device;
• obtaining, from one or more database records of a database, historical information pertaining to one or more services that have been completed, the historical information indicating, for at least one service, a corresponding location, a completion time, and an identity of a field professional that performed the service;
• generating or updating a machine learning model based, at least in part, on the historical information;
• generating, using the machine learning model, a first likelihood value indicating a first likelihood that a first field professional will complete the first service at the first location in a single on-site visit based, at least in part, on a set of attributes of the first service;
• generating, by the one or more servers using the machine learning model, a second likelihood value indicating a second likelihood that a second field professional will complete the first service at the first location in a single on-site visit based, at least in part, on the set of attributes of the first service;
• comparing the first likelihood value and the second likelihood value;
• determining whether the first likelihood value is greater than the second likelihood value;
• assigning the first field professional or the second field professional to perform the first service based, at least in part, on a result of determining whether the first likelihood value is greater than the second likelihood value;
• and
• updating the machine learning model based, at least in part, on information pertaining to the first service after assigning the first field professional to perform the first service.