Machine-learned validation framework

A method comprising:

• receiving, from a first device, a request to route a payload to a destination, the payload indicating a size and a type;
• providing the size and the type into a supervised machine learning model, the supervised machine learning model trained to apply a label to the payload by:
• inputting training data into an unsupervised machine learning model, each entry of the training data including respective size and type information, wherein the unsupervised machine learning model clusters the training data into two or more clusters, at least one of the two or more clusters identified as an outlier cluster;
• and
• applying respective labels to respective size and type pairs of the training data, the applied labels indicating for the outlier cluster a validation function is to be performed before the payload is routed to the destination;
• receiving, as output from the supervised machine learning model, an indication to perform the validation function;
• and
• responsive to receiving the indication, transmitting the payload to a validation destination at a second device.

A system comprising:

• memory with instructions encoded thereon;
• and
• one or more processors that, when executing the instructions, are caused to perform operations comprising:
• receiving, from a first device, a request to route a payload to a destination, the payload indicating a size and a type;
• providing the size and the type into a supervised machine learning model, the supervised machine learning model trained to apply a label to the payload by:
• inputting training data into an unsupervised machine learning model, each entry of the training data including respective size and type information, wherein the unsupervised machine learning model clusters the training data into two or more clusters, at least one of the two or more clusters identified as an outlier cluster;
• and
• applying respective labels to respective size and type pairs of the training data, the applied labels indicating for the outlier cluster a validation function is to be performed before the payload is routed to the destination;
• receiving, as output from the supervised machine learning model, an indication to perform the validation function;
• and
• responsive to receiving the indication, transmitting the payload to a validation destination at a second device.