Predictive, machine-learning, locale-aware computer models suitable for location- and trajectory-aware training sets

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

obtaining, with one or more processors, for a plurality of entities, entity logs, wherein:

the entity logs comprise events involving the entities,

a first subset of the events are actions by the entities,

at least some of the actions by the entities are targeted actions, and

the events are labeled according to an ontology of events having a plurality of event types;

training, with one or more processors, based on the entity logs, a predictive machine learning model to predict whether an entity characterized by a set of inputs to the model will engage in a targeted action in a given geographic locale in the future, wherein:

the predictive machine learning model is based on a plurality of decision trees combined with an ensemble procedure;

the ensemble procedure is boosting, random forest or other form of bootstrap aggregation, or rotation forest; and

at least some of the decision trees are trained with classification and regression tree by recursively splitting a feature space of inputs to the predictive machine learning model along different dimensions of the feature space at values of respective dimensions that locally optimize the respective split to minimize entropy of Gini impurity of targeted actions and non-targeted actions on each side of respective splits; and

storing, with one or more processors, the trained predictive machine learning model in memory.

2. The medium of claim 1 , wherein:

the trained model is configured to make predictions based on features of entity logs indicative of location measurements of events outside to targeted geographic locale; and

the operations comprise predicting whether a given entity will engage in a targeted action with the trained predictive machine learning at least in part by:

obtaining a given entity log of the given entity;

determining a plurality of features from the given entity log, the plurality of features having fewer dimensions than the given entity log; and

inputting the determined plurality of features into the trained predictive machine learning model to cause the model to output a value indicative of the whether the given entity will engage in a targeted action within the geographic locale in the future.

3. The medium of claim 1 , wherein:

the predictive machine learning model comprises a cyclic directed graph of perceptrons; and

weights and biases of the cyclic directed graph of perceptrons are adjusted by unrolling the cycles and iteratively, until a stopping condition:

determining a partial derivative of an objective function relative to each weight and bias, the objective function being based on an amount of aggregate error between predictions of the model and a training set; and

adjusting the weights and biases in directions that the partial derivatives indicate locally optimize the objective function by reducing the amount of error.

4. The medium of claim 1 , wherein:

the predictive machine learning model comprises a recurrent neural network.

5. The medium of claim 1 , wherein:

the predictive machine learning model comprises a long-short term memory model.

6. The medium of claim 1 , comprising, before training, transforming each entity log into a collection of features to which the predictive machine learning model is capable of responding and training the model on the resulting features.

7. The medium of claim 6 , wherein at least some of the features are determined by classifying whether a given type of non-targeted action event occurred with a range of geographic locale outside to a targeted action in geographic locale.

8. The medium of claim 6 , wherein:

wherein the trained model is configured to make predictions based on features of entity logs indicative of roaming patterns of events prior to targeted actions; and

at least some of the features are determined by classifying a roaming amount associated with a given type of non-targeted action event occurred with a distance range of geographic locale outside to a targeted geographic locale action.

9. The medium of claim 6 , wherein at least some of the features are determined based on a roaming amount a first type of non-targeted action event occurred outside to a targeted geographic locale.

10. The medium of claim 6 , wherein a given one of the features is determined based on a distance measure between the geographic locale a first type of non-targeted action event occurred prior to a targeted action and based a distance measure of a second type of non-targeted action event occurred outside to a targeted geographic locale.

11. The medium of claim 6 , wherein a given one of the features is determined based on first roaming measure and based on a first roaming measure a first type of non-targeted action event occurred outside to a designed targeted geographic locale.

12. The medium of claim 11 , wherein the given one of the features is determined based on second roaming measure and based on a roaming measure a second type of non-targeted action event occurred outside the designed targeted geographic locale.

13. The medium of claim 1 , wherein:

a second subset of events are actions taken on the entities by others;

at least some features upon which the model is trained are based on events in the second subset; and

at least some features upon which the model is trained are based on events in the first subset.

14. The medium of claim 1 , wherein:

the entities include consumers;

the events include communications to consumers by an enterprise;

the events include purchases by consumers from the enterprise;

the events include non-purchase interactions by consumers with the enterprise; and

the entity logs are obtained from a customer relationship management system of the enterprise.

15. The medium of claim 14 , wherein:

the enterprise is a credit card issuer and the trained predictive machine learning model is configured to predict whether a consumer will default;

the enterprise is a lender and the trained predictive machine learning model is configured to predict whether a consumer will borrow;

the enterprise is an insurance company and the trained predictive machine learning model is configured to predict whether a consumer will file a claim;

the enterprise is a wireless company and the trained predictive machine learning model is configured to predict whether a consumer will sign-up for service renewal;

the enterprise is a vehicle seller and the trained predictive machine learning model is configured to predict whether a consumer will purchase a vehicle; or

the enterprise is a seller of goods and the trained predictive machine learning model is configured to predict whether a consumer will file a warranty claim.

16. The medium of claim 1 , wherein:

the trained predictive machine learning model is configured to output a plurality of scores each indicative of likelihood of an entity engaging in a targeted behavior in a different respective geographic locale in the future.

17. The medium of claim 1 , wherein:

the trained predictive machine learning model is configured to output a plurality of scores each indicative of likelihood of an entity engaging in a different respective targeted behavior in the given geographic locale in the future.

18. The medium of claim 1 , comprising:

inputting more than 1,000 entity logs corresponding to more than 1,000 entities into the trained machine learning model; and

selecting a subset of the more than 1,000 entities predicted to engage in a targeted action by the trained predictive machine learning model.

19. The medium of claim 16 , comprising:

causing one or more messages to be sent to members of a selected subset of entities responsive to the selection.

20. The medium of claim 1 , wherein training comprises means for training.

21. The medium of claim 1 , wherein the ontology of events comprise at least two type of feature engineering listed below:

distance feature engineering,

roaming feature engineering,

semantic embedding feature engineering, and

modal feature engineering.

22. The medium of claim 1 , comprising:

steps for predicting whether an entity will engage in a targeted behavior in the future.

23. The medium of claim 1 , where the given geographic locale corresponds to a:

geographic area,

administrative area,

point of interest,

geographic area tuple,

embedded geographic area pair,

geo-temporal sentence,

set of point of interest,

trajectory,

indoor area,

outdoor area,

communication channel;

area served by a wireless transmitter or receiver, or

taxation area.

24. A method, comprising:

obtaining, with one or more processors, for a plurality of entities, entity logs, wherein:

the entity logs comprise events involving the entities,

a first subset of the events are actions by the entities,

at least some of the actions by the entities are targeted actions, and

the events are labeled according to an ontology of events having a plurality of event types;

training, with one or more processors, based on the entity logs, a predictive machine learning model to predict whether an entity characterized by a set of inputs to the model will engage in a targeted action in a given geographic locale in the future, wherein:

the predictive machine learning model is based on a plurality of decision trees combined with an ensemble procedure;

the ensemble procedure is boosting, random forest or other form of bootstrap aggregation, or rotation forest; and

at least some of the decision trees are trained with classification and regression tree by recursively splitting a feature space of inputs to the predictive machine learning model along different dimensions of the feature space at values of respective dimensions that locally optimize the respective split to minimize entropy of Gini impurity of targeted actions and non-targeted actions on each side of respective splits; and

storing, with one or more processors, the trained predictive machine learning model in memory.