Machine learning techniques for automated processing of workflow approval requests

A non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device:

• to generate a machine learning model for workflow approval requests, wherein generating the machine learning model comprises automatically learning one or more temporal-based patterns from historical data related to one or more previous workflow approval requests;
• to generate, in response to an additional workflow approval request, an output value of the machine learning model by applying the machine learning model to input data related to the additional workflow approval request;
• to compare the output value to at least one predefined threshold value;
• and
• to automatically reject the additional workflow approval request responsive to a result of the comparing of the output value to the at least one predefined threshold value.

An apparatus comprising:

• at least one processing device comprising a processor coupled to a memory;
• the at least one processing device being configured:
• to generate a machine learning model for workflow approval requests, wherein generating the machine learning model comprises automatically learning one or more temporal-based patterns from historical data related to one or more previous workflow approval requests;
• to generate, in response to an additional workflow approval request, an output value of the machine learning model by applying the machine learning model to input data related to the additional workflow approval request;
• to compare the output value to at least one predefined threshold value;
• and
• to automatically reject the additional workflow approval request responsive to a result of the comparing of the output value to the at least one predefined threshold value.