Monitoring and controlling continuous stochastic processes based on events in time series data

1. A tangible, non-transitory, machine-readable medium storing instructions that when executed by one or more processors effectuate operations comprising:

obtaining, with a computer system, one or more out of a plurality of datasets having a plurality of interaction-event records, wherein:

the interaction-event records describe respective interaction events,

the interaction-events are interactions in which a first entity has experiences or obtains other information pertaining to second entity, and

at least some of the interaction-event records are associated with respective risks by which sequences of at least some of the interaction events relative to one another are ascertainable;

determining, with a continuous stochastic process controller executed by multiple computing devices of the computer system, based on at least some of the interaction-event records, sets of event-risk scores, the sets corresponding to at least some of the interaction events, wherein:

at least some respective event-risk scores are indicative of an effective of a respective risk ascribed by the first entity to a respective aspect of the second entity; and

at least some respective event-risk scores are based on both:

respective contributions of respective corresponding events to a subsequent event in the one or more out of the plurality of datasets, and

a risk ascribed to a subsequent event in the one or more out of the plurality of datasets, the subsequent event occurring after the respective corresponding events; and

storing, with the computer system, the sets of event-risk scores in memory.

2. The medium of claim 1 , wherein:

for at least a plurality of the interaction events, a set of event-risk scores is determined for the respective interaction-event among the plurality of the interaction-events.

3. The medium of claim 1 , wherein:

each of at least some of the sets of event-risk scores include a plurality of different scores corresponding to different requests of the second entity to which the first entity ascribes respective risks.

4. The medium of claim 3 , wherein:

the request includes request of a collateralized offering, request of a collateralized offering, a request of a new offering, a modification of existing offering, obtaining a product at a cost that is subsidized in exchange for a promise of future behavior, or insurance.

5. The medium of claim 3 , wherein:

different offerings are associated with different sets of risk profiles.

6. The medium of claim 1 , wherein:

where when the event-risk score of a plurality of interaction events fits within a preset or dynamically determined simplex, in response, a set of interaction-events is initiated.

7. The medium of claim 1 , wherein, for at least some of the sets of event-risk scores, each respective set includes both:

a respective weight corresponding to a contribution of the respective interaction event toward influencing the first entity to cause the subsequent event, and

a respective risk index based on a product of respective weight and a risk ascribed to the subsequent event by the second entity.

8. The medium of claim 1 , wherein:

the events include both transaction and non-transaction events;

the events include both direct and indirect interactions;

the events include factors, demographic, or macro-economic events;

the events include credit score;

the events include timing classifications of events;

the event includes social media information;

the interaction-event records are obtained from diverse data sets; or

at least some of the event-risk scores are determined at least in part with a machine learning classifier.

9. The medium of claim 1 , wherein:

the events include both transaction and non-transaction events;

the events include both direct and indirect interactions;

the events include factors, demographic, or macro-economic events;

the events include credit score;

the event includes social media information;

the interaction-event records are obtained from diverse data sets; and

at least some of the event-risk scores are determined at least in part with a machine learning classifier.

10. The medium of claim 1 , wherein:

the events include factors, demographic, or macro-economic events;

the events include credit score;

the events include social media information; and

the events include Know Your Client rules;

the interaction-event records are obtained from diverse data sets; or

at least some of the event-risk scores are determined at least in part with a machine learning classifier.

11. The medium of claim 1 , wherein determining sets of event-risk scores comprises:

determining initial risks of at least one type of score in the sets of event-risk scores; and

iteratively adjusting the at least one type of score with machine learning.

12. The medium of claim 1 , comprising:

obtaining a designation of one of the events as a reference event;

obtaining a risk ascribed to the reference event by the first entity;

selecting a portion of an event timeline including a subset of the events among which is the reference event;

determining, using a classifier, relative risks for at least some events in the subset; and

assigning a risk index to individual events among the subset.

13. The medium of claim 1 , the operations comprising:

selecting a type of interaction for the first entity to experience in the future based on the sets of event-risk scores stored in memory.

14. The medium of claim 1 , wherein:

the events include both real interactions synthesized interactions.

15. The medium of claim 1 , comprising:

obtaining a designation of one of the events as a reference event;

obtaining a risk ascribed to the reference event by the first entity;

selecting a portion of an event timeline including a subset of the events among which is the reference event;

determining, using a classifier, relative risks for at least some events in the subset;

assigning a risk index to individual events among the subset; and

setting or resetting parameters of one or more transactions with second entity.

16. The medium of claim 1 , comprising:

determining a measure of a contribution of a given event or type of events to an event-risk score for an individual among the sets of event-risk scores; and

causing a visual indication of measure of a contribution of a given event or type of events to be presented to indicate how to modify the event-risk score for the individual.

17. The medium of claim 1 , comprising:

steps for monitoring or controlling a continuous stochastic process.

18. The medium of claim 1 , wherein:

determining sets of event-risk scores comprises determining sets of event-risk scores with a dynamic Bayesian network.

19. The medium of claim 1 , wherein:

determining sets of event-risk scores comprises determining sets of event-risk scores with a directed cyclic graph of perceptrons.

20. The medium of claim 1 , wherein the continuous stochastic process controller comprises a transformer architecture that maps events and relationships therebetween to a continuous space vector representation of lower dimensionality than the mapped events, wherein location in the vector space is indicative of risk.

21. The medium of claim 1 , wherein the continuous stochastic process controller comprises multiheaded attention.

22. The medium of claim 1 , wherein the continuous stochastic process controller comprises:

a data classifier,

a model trainer,

a risk-scoring model,

a risk-score repository,

a control module, and

an explainability module.

23. The medium of claim 1 , wherein the continuous stochastic process controller comprises:

a data classifier,

a model trainer,

a risk-scoring model,

a risk-score repository,

a control module, or

an explainability module.

24. A method, comprising:

obtaining, with a computer system, one or more out of a plurality of datasets having a plurality of interaction-event records, wherein:

the interaction-event records describe respective interaction events,

the interaction-events are interactions in which a first entity has experiences or obtains other information pertaining to second entity, and

at least some of the interaction-event records are associated with respective risks by which sequences of at least some of the interaction events relative to one another are ascertainable;

determining, with a continuous stochastic process controller executed by the computer system, based on at least some of the interaction-event records, sets of event-risk scores, the sets corresponding to at least some of the interaction events, wherein:

at least some respective event-risk scores are indicative of an effective of a respective risk ascribed by the first entity to a respective aspect of the second entity; and

at least some respective event-risk scores are based on both:

respective contributions of respective corresponding events to a subsequent event in the one or more out of the plurality of datasets, and

a risk ascribed to a subsequent event in the one or more out of the plurality of datasets, the subsequent event occurring after the respective corresponding events; and

storing, with the computer system, the sets of event-risk scores in memory.

25. The medium of claim 1 , wherein the operations comprise:

training, with the continuous stochastic process controller, based on the interaction-event records, a risk-scoring machine learning model, wherein after training, the risk-scoring machine learning model is operative to model a stochastic attribute that is updated as events are received via a plurality of event streams.

26. The medium of claim 25 , wherein:

the interaction-events are interactions in which a first entity has experiences or obtains other information pertaining to a set of more than 10,000 other entities, the set including the second entity; and

the risk-scoring machine learning model is updated within less than 500 milliseconds of receiving a given event in one of the streams.