Machine-learned validation framework
A system and a method are disclosed herein for machine-learned detection of outliers within payload requests. An entity management system uses machine learning to cluster data characterizing requests from entities to route payloads, and determines one or more data clusters that are outliers. The system receives a request to route a payload to a destination, and applies a supervised machine learning model to size and type information indicated by the payload. The supervised machine learning model applies a label to the payload data (e.g., indicating that the payload routing request is an outlier). This outlier detection may drive a validation process to address detected outliers. The system may receive an indication to perform a validation function and transmit the payload to a validation destination. The system may leverage payload data and feedback received from an entity to optimize machine learning techniques to the entity.
1. A non-transitory computer-readable medium comprising memory with instructions encoded thereon, the instructions, when executed, causing one or more processors to perform operations, the instructions comprising instructions to:
receive, from a first device, a request to route a payload to a destination, the payload indicating a size and a type;
provide 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;
receive, as output from the supervised machine learning model, an indication to perform the validation function; and
responsive to receiving the indication, transmit the payload to a validation destination at a second device.
2. The non-transitory computer-readable medium of claim 1 , wherein the instructions further comprise instructions to:
receive feedback from the validation destination, the feedback indicative of an association between the payload and the validation function;
generate, based on the received feedback, a supplemental training set; and
retrain, using the supplemental training set, the supervised machine learning model.
3. The non-transitory computer-readable medium of claim 1 , wherein the supervised machine learning model is further trained to apply the label to the payload by generating a training set using the labeled respective size and type pairs of the training data.
4. The non-transitory computer-readable medium of claim 3 , wherein the instructions further comprise instructions to train the supervised machine learning model using the training set.
5. The non-transitory computer-readable medium of claim 1 , wherein the respective size and type information is representative of payloads from a plurality of entities.
6. The non-transitory computer-readable medium of claim 1 , wherein the size corresponds to an amount of time needed by an entity to perform a function.
7. The non-transitory computer-readable medium of claim 1 , wherein the instructions further comprise instructions to perform the validation function.
8. The non-transitory computer-readable medium of claim 7 , wherein the instructions to perform the validation function comprises instructions to:
determine a plurality of payload validators;
receive, from a first payload validator of the plurality of payload validators, a first validation resolution; and
receive, from a second payload validator of the plurality of payload validators, a second validation resolution.
9. The non-transitory computer-readable medium of claim 7 , wherein the instructions to perform the validation function comprises instructions to:
reject the request to route the payload to the destination;
determine, based on characteristics of the outlier cluster, a recommended modification to the request; and
transmit the recommended modification to the first device.
10. The non-transitory computer-readable medium of claim 1 , wherein the two or more clusters are associated with respective levels of deviation from an expected size range.
11. The non-transitory computer-readable medium of claim 1 , wherein a cluster of the two or more clusters is a non-outlier cluster, a non-outlier label applied to the non-outlier cluster indicates that the request to route the payload to the destination is authorized.
12. 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.
13. The method of claim 12 , further comprising:
receiving feedback from the validation destination, the feedback indicative of an association between the payload and the validation function;
generating, based on the received feedback, a supplemental training set; and
retraining, using the supplemental training set, the supervised machine learning model.
14. The method of claim 12 , wherein the two or more clusters are associated with respective levels of deviation from an expected size range.
15. The method of claim 12 , wherein a cluster of the two or more clusters is a non-outlier cluster, a non-outlier label applied to the non-outlier cluster indicates that the request to route the payload to the destination is authorized.
16. The method of claim 12 , wherein the supervised machine learning model is further trained to apply the label to the payload by generating a training set using the labeled respective size and type pairs of the training data, further comprising training the supervised machine learning model using the training set.
17. 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.
18. The system of claim 17 , wherein the operations further comprise:
receiving feedback from the validation destination, the feedback indicative of an association between the payload and the validation function;
generating, based on the received feedback, a supplemental training set; and
retraining, using the supplemental training set, the supervised machine learning model.
19. The system of claim 17 , wherein a cluster of the two or more clusters is a non-outlier cluster, a non-outlier label applied to the non-outlier cluster indicates that the request to route the payload to the destination is authorized.
20. The system of claim 17 , wherein the supervised machine learning model is further trained to apply the label to the payload by generating a training set using the labeled respective size and type pairs of the training data, further comprising training the supervised machine learning model using the training set.