Testing predicted data utilizing trained machine learning model

1 . A computing system, comprising:

a memory device; and

a processing device operatively coupled to the memory device, wherein the processing device is configured to execute computer-readable program code to:

iteratively train, using training data comprising a personal data set of a plurality of first users, a predictive model incorporating a machine learning program, the predictive model including a neural network that performs cluster analysis via unsupervised learning, the personal data set including a data entry regarding an assessment score determined with respect to each respective first user, the predictive model being trained to predict a financial health assessment score for each respective first user, wherein the financial health assessment score is determined based on input responses received from each respective first user to a financial health assessment survey, wherein the training of the predictive model includes:

ingesting electronically received responses to the financial health assessment survey to be included as part of the training data:

performing automated data validation on the responses to verify that distributional statistics of the responses fall within expected bounds;

inserting the training data that includes the responses into an iterative training and testing loop to predict a target variable; and

repeatedly predicting the target variable during each iteration of the training and testing loop, wherein each iteration of the training and testing loop has differing weights applied to one or more nodes of the machine learning program, each of the differing weights being updated with each iteration of the training and testing loop to reduce error in predicting the target variable and automatically pausing the iterative training and testing loop upon detection of any anomaly until corrective action is taken, which improves predictability of the target variable and functionality of the predictive model;

deploy the trained predictive model;

predict, using the trained predictive model, a predicted assessment score of a second user associated with a user device, the predicting of the predicted assessment score including the trained predictive model correlating a personal data set of the second user to the personal data set of at least one of the first users, wherein the predicted assessment score includes a numeric assessment score associated with the financial health of the second user;

generate a test personal data set with respect to the second user, the test personal data set including a first data entry changed from the personal data set of the second user, the change of the first data entry corresponding to a change in a relationship between the second user and a first entity;

predict, by the trained predictive model, a test predicted assessment score of the second user, the predicting of the test predicted assessment score including the trained predictive model correlating the test personal data set of the second user to the personal data set of at least one of the first users;

when a difference between the predicted assessment score and the test predicted assessment score meets or exceeds a threshold value, write, to the memory device, account-related data that updates an account setting of the second user and thereby reconfigures operation of the computing system with respect to subsequent communications to the user device;

send a communication to the user device of the second user including content relating to the change in the relationship between the second user and the first entity; and

upon generating the predicted assessment score and the test predicted assessment score, trigger a change in the computing system to reflect the contents of the predicted assessment score and the test predicted assessment score.

2 . The computing system of claim 1 , wherein the change in the relationship between the second user and the first entity corresponds to the second user purchasing a product and/or service from the first entity.

3 . The computing system of claim 1 , wherein the change in the relationship between the second user and the first entity corresponds to a change in an account setting of the second user.

4 . The computing system of claim 3 , wherein the change in the account setting of the second user includes a change in at least one of a form, a frequency, or a content of future communications sent from the computing system to the user device.

5 . The computing system of claim 3 , wherein the change in the account setting of the second user includes a change in a manner in which the second user interacts with the computing system when navigating a software application executed on the user device.

6 . The computing system of claim 1 , wherein the communication includes an offer for sale of a product and/or service offered by the first entity.

7 . The computing system of claim 1 , wherein the communication includes a request for approval to change an account setting of the second user.

8 . The computing system of claim 7 , wherein the change in the account setting of the second user includes a change in at least one of a form, a frequency, or a content of future communications sent from the computing system to the user device.

9 . The computing system of claim 7 , wherein the change in the account setting of the second user includes a change in a manner in which the second user interacts with the computing system when navigating a software application executed on the user device.

10 . The computing system of claim 1 , wherein the communication includes a request for approval for the first entity to discontinue providing a product and/or service to the second user.

11 . The computing system of claim 1 , wherein the personal data set of the second user includes demographic data.

12 . The computing system of claim 11 , wherein the personal data set of the second user further includes behavioral data regarding at least one of the past activities of the second user and/or the past activities of the computing system taken with respect to the second user.

13 . The computing system of claim 11 , wherein the personal data set of the second user includes data regarding past interactions between the computing system and the second user via the user device.

14 . The computing system of claim 11 , wherein the personal data set of the second user includes data regarding a product and/or service provided by an entity associated with the computing system.

15 . A computing system, comprising:

a memory device; and

a processing device operatively coupled to the memory device, wherein the processing device is configured to execute computer-readable program code to:

iteratively train, using training data comprising a personal data set of a plurality of first users, a predictive model incorporating a machine learning program, the predictive model including a neural network that performs cluster analysis via unsupervised learning, the personal data set including a data entry regarding an assessment score determined with respect to each respective first user, the predictive model being trained to predict a financial health assessment score for each respective first user, wherein the financial health assessment score is determined based on input responses received from each respective first user to a financial health assessment survey, wherein the training of the predictive model includes:

ingesting electronically received responses to the financial health assessment survey to be included as part of the training data;

performing automated data validation on the responses to verify that distributional statistics of the responses fall within expected bounds:

inserting the training data that includes the responses into an iterative training and testing loop to predict a target variable; and

repeatedly predicting the target variable during each iteration of the training and testing loop, wherein each iteration of the training and testing loop has differing weights applied to one or more nodes of the machine learning program, each of the differing weights being updated with each iteration of the training and testing loop to reduce error in predicting the target variable and automatically pausing the iterative training and testing loop upon detection of any anomaly until corrective action is taken, which improves predictability of the target variable and functionality of the predictive model;

deploy the trained predictive model;

predict, using the trained predictive model, a predicted assessment score of a second user associated with a user device, the predicting of the predicted assessment score including the trained predictive model correlating a personal data set of the second user to the personal data set of at least one of the first users, wherein the predicted assessment score includes a numeric assessment score associated with the financial health of the second user;

generate a test personal data set with respect to the second user, the test personal data set including a first data entry changed from the personal data set of the second user, the change of the first data entry corresponding to a change in a relationship between the second user and a first entity;

predict, by the trained predictive model, a test predicted assessment score of the second user, the predicting of the test predicted assessment score including the trained predictive model correlating the test personal data set of the second user to the personal data set of at least one of the first users; and

change an account setting of the second user stored to the memory device when a difference between the predicted assessment score and the test predicted assessment score meets or exceeds a threshold value, the changing of the account setting reconfiguring operation of the computing system with respect to subsequent communications to the user device.

16 . The computing system of claim 15 , wherein the change in the account setting of the second user includes a change in at least one of a form, a frequency, or a content of future communications sent from the computing system to the user device.

17 . The computing system of claim 15 , wherein the change in the account setting of the second user includes a change in a manner in which the second user interacts with the computing system when navigating a software application executed on the user device.

18 . A computer-implemented method, comprising:

iteratively training, using training data comprising a personal data set of a plurality of first users, a predictive model incorporating a machine learning program, the predictive model including a neural network that performs cluster analysis via unsupervised learning, the personal data set including a data entry regarding an assessment score determined with respect to each respective first user, the predictive model being trained to predict a financial health assessment score for each respective first user, wherein the financial health assessment score is determined based on input responses received from each respective first user to a financial health assessment survey, wherein the training of the predictive model includes:

ingesting electronically received responses to the financial health assessment survey to be included as part of the training data;

performing automated data validation on the responses to verify that distributional statistics of the responses fall within expected bounds;

inserting the training data that includes the responses into an iterative training and testing loop to predict a target variable; and

repeatedly predicting the target variable during each iteration of the training and testing loop, wherein each iteration of the training and testing loop has differing weights applied to one or more nodes of the machine learning program, each of the differing weights being updated with each iteration of the training and testing loop to reduce error in predicting the target variable and automatically pausing the iterative training and testing loop upon detection of any anomaly until corrective action is taken, which improves predictability of the target variable and functionality of the predictive model;

deploying the trained predictive model;

predicting, using the trained predictive model, a predicted assessment score of a second user associated with a user device, the predicting of the predicted assessment score including the trained predictive model correlating a personal data set of the second user to the personal data set of at least one of the first users, wherein the predicted assessment score includes a numeric assessment score associated with the financial health of the second user;

generating a test personal data set with respect to the second user, the test personal data set including a first data entry changed from the personal data set of the second user, the change of the first data entry corresponding to a change in a relationship between the second user and a first entity;

predicting, by the trained predictive model, a test predicted assessment score of the second user, the predicting of the test predicted assessment score including the trained predictive model correlating the test personal data set of the second user to the personal data set of at least one of the first users;

when a difference between the predicted assessment score and the test predicted assessment score meets or exceeds a threshold value, writing, to the memory device, account-related data that updates an account setting of the second user and thereby reconfigures operation of the computing system with respect to subsequent communications to the user device;

sending a communication to the user device of the second user including content relating to the change in the relationship between the second user and the first entity; and

upon generating the predicted assessment score and the test predicted assessment score, triggering a change in the computing system to reflect the contents of the predicted assessment score and the test predicted assessment score.

19 . The computer-implemented method of claim 18 , wherein the change in the relationship between the second user and the first entity corresponds to the second user purchasing a product and/or service from the first entity.

20 . The computer-implemented method of claim 18 , wherein the change in the relationship between the second user and the first entity corresponds to a change in an account setting of the second user.