Federated machine-learning platform leveraging engineered features based on statistical tests
Provided is a process including: receiving a data token to be passed from a first node to a second node; retrieving machine learning model attributes from a collection of one or more of the sub-models of a federated machine-learning model; determining based on the machine learning model attributes, that the data token is learning relevant to members of the collection of one or more of the sub-models and, in response, adding the data toke to a training set to be used by at least some members of the collection of one or more of the sub-models; determining a collection of data tokens to transmit from the second node to a third node of the set of nodes participating in a federated machine-learning model; and transmitting the collection of data tokens.
1. A tangible, non-transitory, machine-readable medium storing instructions that when executed by one or more processors effectuate operations comprising:
receiving, with a computer system, a data token to be passed from a first node to a second node, wherein:
the first node and second nodes are members of a set of nodes participating in a federated machine-learning model executed by the computer system,
the federated machine-learning model comprises an application-layer network of sub-models of the federated machine-learning model,
different members of the set of nodes control different subsets of the sub-models in the application-layer network,
the data token corresponding to data upon which the federated machine-learning model operates, and
the data token is not among data upon which a sub-model of the second node was trained;
retrieving, with the computer system, machine learning model attributes from a collection of one or more of the sub-models of the federated machine-learning model;
determining, with the computer system, based on the machine learning model attributes, that the data token is learning relevant to members of the collection of one or more of the sub-models with means for statistics testing and, in response, adding the data token to a training set to be used by at least some members of the collection of one or more of the sub-models;
determining, with the computer system, a collection of data tokens to transmit from the second node to a third node of the set of nodes participating in a federated machine-learning model;
transmitting, with the computer system, the collection of data tokens from the second node to the third node across an interface between the second node and the third node;
obtaining, with the computer system, for a plurality of entities corresponding to the set of nodes, datasets, wherein:
the datasets comprise events involving the plurality of entities;
the datasets comprise or are otherwise associated with attributes of the plurality of entities; and
the events are distinct from the attributes;
forming, with the computer system, a plurality of objects, wherein each object of the plurality of objects comprises a different set of attributes and events;
forming, with the computer system, a library of classes with a plurality of object-orientation modelors;
forming, with the computer system, a plurality of object-manipulation functions, each function being configured to leverage a respective class among the library of classes;
receiving, with the computer system, a request from a first entity from the plurality of entities to determine a set of actions to achieve, or increase the likelihood of, a given targeted action;
assigning, with the computer system, the given targeted action to a first subset of classes from the library of classes;
determining, with the computer system, based on the assigning, the set of actions to achieve, or increase likelihood of, the given targeted action using a first subset of the plurality of object-manipulation functions leveraging the first subset of classes from the library of classes;
forming a third training dataset from the datasets;
training a third machine-learning model on the third training dataset by adjusting parameters of the third machine-learning model to optimize a third objective function that indicates interdependency of the plurality of object-manipulation functions in leveraging a specific class;
forming an interdependency graph using, at least in part, the third objective function, wherein the interdependency graph comprises a plurality of execution triggers, wherein each execution trigger from the plurality of execution triggers comprises a subset of the object-manipulation functions; and
storing the adjusted parameters of the trained third machine-learning model in memory.
2. The medium of claim 1 , wherein determining that the data token is learning relevant comprises determining a measure of a behavioral impact of the data token on an entity modeled by the federated machine-learning model.
3. The medium of claim 2 , wherein the measure of the behavioral impact is indicative of a change in expected spending over time, location, or products.
4. The medium of claim 1 , wherein determining the set of actions to achieve, or increase the likelihood of, the given targeted action further comprises:
forming a first training dataset from the datasets;
training, with one or more processors, a first machine-learning model on the first training dataset by adjusting parameters of the first machine-learning model to optimize a first objective function that indicates an accuracy of the first subset of the plurality of object-manipulation functions in leveraging the first subset of classes from the library of classes; and
storing, with one or more processors, the adjusted parameters of the trained first machine-learning model in memory.
5. The medium of claim 4 , wherein training comprises steps for training.
6. The medium of claim 4 , wherein:
at least some of the data in the first training dataset is obtained from the first entity.
7. The medium of claim 1 , the operations further comprising:
forming a second training dataset from the datasets;
training, with one or more processors, a second machine-learning model on the second training dataset by adjusting parameters of the second machine-learning model to optimize a second objective function that indicates an accuracy of the plurality of object-orientation modelors in generating the library of classes; and
storing the adjusted parameters of the trained second machine-learning model in memory.
8. The medium of claim 1 , wherein:
at least some of the obtained datasets are processed datasets, prepared by the corresponding entities from the plurality of entities, to not reveal more than a threshold amount of information.
9. The medium of claim 8 , wherein:
the processed datasets are prepared, by the corresponding entities from the plurality of entities, based on a set of rules, wherein the set of rules comprises cybersecurity and privacy policies.
10. The medium of claim 1 , wherein the datasets comprise:
consumers;
communications to consumers by an enterprise;
communications to an enterprise by consumers;
purchases by consumers from an enterprise;
non-purchase interactions by consumers with an enterprise; or
a customer relationship management system of an enterprise; and wherein:
the enterprise is a credit card issuer and the given targeted action is predicting whether a consumer will default;
the enterprise is a lender and the given targeted action is predicting whether a consumer will borrow;
the enterprise is an insurance company and the given targeted action is predicting whether a consumer will file a claim;
the enterprise is an insurance company and the given targeted action is predicting whether a consumer will sign-up for insurance;
the enterprise is a vehicle seller and the given targeted action is predicting whether a consumer will purchase a vehicle;
the enterprise is a seller of goods and the given targeted action is predicting whether a consumer will file a warranty claim;
the enterprise is a wireless operator and the given targeted action is predicting whether a consumer upgrade their cellphone; or
the enterprise is a bank and the given targeted action is predicting GDP variation.
11. The medium of claim 1 , wherein the plurality of object-manipulation functions comprises:
a sequence function used to change a collection of events into a time sequence for processing;
a feature function used to gather features of a first object-orientation modelor and then use the features in a second object-orientation modelor; and
an ensembling function used to combine a first subset of the library of classes.
12. The medium of claim 1 , wherein the plurality of object-orientation modelors comprises:
a scaled propensity modelor used to calculate probability of a customer making an economic commitment;
a timing modelor used to calibrate moments in time when a customer is likely to engage with the given targeted action;
an affinity modelor used to capture ranked likes and dislikes of an entity's customers for a first subset of targeted actions;
a best action modelor used to create a framework for concurrent Key Performance Index of the given targeted action at different points in a customer's journey; and
a cluster modelor used to group an entity's customers based on the customers' behavior into a finite list.
13. The medium of claim 1 , the operations further comprising:
forming an interdependency graph using, at least in part, ontology semantics by leveraging feature engineering modelors, wherein the feature engineering modelors comprise:
recency feature engineering modelors;
frequency feature engineering modelors;
lag feature engineering modelors;
difference feature engineering modelors; or
harmonic analysis feature engineering modelors.
14. The medium of claim 13 , wherein the ontology semantics comprise a concurrent ontology labeling datastore (COLD) methodology.
15. The medium of claim 1 , wherein:
the interdependency graph comprises a plurality of execution schedules, wherein each execution schedule from the plurality of execution schedules comprises a subset of the object-manipulation functions.
16. The medium of claim 1 , wherein the attributes comprising:
entity restrictions for at least some of the plurality of entities;
entity business protocols for at least some of the plurality of entities;
entity policies for at least some of the plurality of entities;
entity authorized users for at least some of the plurality of entities; and
entity security protocols for at least some of the plurality of entities.
17. The medium of claim 1 , wherein:
at least some of the datasets are updated in real-time.
18. The medium of claim 1 , wherein:
at least some of the datasets are updated using a record level stream.
19. A method, comprising:
receiving, with a computer system, a data token to be passed from a first node to a second node, wherein:
the first node and second nodes are members of a set of nodes participating in a federated machine-learning model executed by the computer system,
the federated machine-learning model comprises an application-layer network of sub-models of the federated machine-learning model,
different members of the set of nodes control different subsets of the sub-models in the application-layer network,
the data token corresponding to data upon which the federated machine-learning model operates, and
the data token is not among data upon which a sub-model of the second node was trained;
retrieving, with the computer system, machine learning model attributes from a collection of one or more of the sub-models of the federated machine-learning model;
determining, with the computer system, based on the machine learning model attributes, that the data token is learning relevant to members of the collection of one or more of the sub-models with means for statistics testing and, in response, adding the data token to a training set to be used by at least some members of the collection of one or more of the sub-models;
determining, with the computer system, a collection of data tokens to transmit from the second node to a third node of the set of nodes participating in a federated machine-learning model;
transmitting, with the computer system, the collection of data tokens from the second node to the third node across an interface between the second node and the third node;
obtaining, with the computer system, for a plurality of entities corresponding to the set of nodes, datasets, wherein:
the datasets comprise events involving the plurality of entities;
the datasets comprise or are otherwise associated with attributes of the plurality of entities; and
the events are distinct from the attributes;
forming, with the computer system, a plurality of objects, wherein each object of the plurality of objects comprises a different set of attributes and events;
forming, with the computer system, a library of classes with a plurality of object-orientation modelors;
forming, with the computer system, a plurality of object-manipulation functions, each function being configured to leverage a respective class among the library of classes;
receiving, with the computer system, a request from a first entity from the plurality of entities to determine a set of actions to achieve, or increase the likelihood of, a given targeted action;
assigning, with the computer system, the given targeted action to a first subset of classes from the library of classes;
determining, with the computer system, based on the assigning, the set of actions to achieve, or increase likelihood of, the given targeted action using a first subset of the plurality of object-manipulation functions leveraging the first subset of classes from the library of classes;
forming a third training dataset from the datasets;
training a third machine-learning model on the third training dataset by adjusting parameters of the third machine-learning model to optimize a third objective function that indicates interdependency of the plurality of object-manipulation functions in leveraging a specific class;
forming an interdependency graph using, at least in part, the third objective function, wherein the interdependency graph comprises a plurality of execution triggers, wherein each execution trigger from the plurality of execution triggers comprises a subset of the object-manipulation functions; and
storing the adjusted parameters of the trained third machine-learning model in memory.