System and method for iterative data clustering using machine learning
AssigneeCvent, Inc.
InventorsLashkar KASHIF, Casey HARTNETT
Life of this patent
Estimating the term…
Abstract
Systems, methods, and non-transitory computer-readable storage media which train a machine learning algorithm using a training set of Requests for Proposals (RFPs), then cluster a second set of RFPs using the trained machine learning algorithm. Distinct clusters are then compared to historical data, and an outlier is identified. An alert regarding that outlier is then transmitted across a network to an entity associated with the outlier.
Claims20
A method comprising:
- training, via a processor, a machine learning algorithm using a training set of Requests for Proposals (RFPs);
- clustering, via a processor executing the machine learning algorithm, a second set of RFPs according to attributes of the second set of RFPs, resulting in at least two clusters, each cluster corresponding to a respective attribute;
- aggregating historical data for a plurality of entities;
- comparing, via the processor, the historical data to the at least two clusters;
- identifying, via the processor, an outlier within the historical data corresponding to a single attribute of the attributes of the second set of RFPs;
- generating, via the processor, an alert based on the outlier;
- and
- transmitting the alert via a network to an entity within the plurality of entities associated with the outlier.
A system comprising:
- a processor;
- and
- a non-transitory computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
- training a machine learning algorithm using a training set of Requests for Proposals (RFPs);
- clustering, by executing the machine learning algorithm, a second set of RFPs according to attributes of the second set of RFPs, resulting in at least two clusters, each cluster corresponding to a respective attribute;
- aggregating historical data for a plurality of entities;
- comparing the historical data to the at least two clusters;
- identifying an outlier within the historical data corresponding to a single attribute of the attributes of the second set of RFPs;
- generating an alert based on the outlier;
- and
- transmitting the alert via a network to an entity within the plurality of entities associated with the outlier.
A non-transitory computer-readable storage medium having instructions stored which, when executed by a processor, cause the processor to perform operations comprising:
- training a machine learning algorithm using a training set of Requests for Proposals (RFPs);
- clustering, by executing the machine learning algorithm, a second set of RFPs according to attributes of the second set of RFPs, resulting in at least two clusters, each cluster corresponding to a respective attribute;
- aggregating historical data for a plurality of entities;
- comparing the historical data to the at least two clusters;
- identifying an outlier within the historical data corresponding to a single attribute of the attributes of the second set of RFPs;
- generating an alert based on the outlier;
- and
- transmitting the alert via a network to an entity within the plurality of entities associated with the outlier.
Dependencies are inferred from the claim text.