Systems and methods for predictive data analytics

A method comprising:

• in response to receiving a request indicating a group type and a time frame, by at least one processor communicatively coupled to a memory device,
• generating synthetic historical data, by:
• selecting a set of users from the plurality of users based on the group type;
• retrieving, for the plurality of users, user data and historical data, to create retrieved user data and retrieved historical data;
• identifying a set of new users of the plurality of users during the time frame based on the retrieved user data and the retrieved historical data;
• adding the set of new users to the set of users, to generate an updated set of users;
• and
• generating the synthetic historical data for at least one user from the updated set of users;
• for the at least one user from the updated set of users, computing a likelihood of a prescription drug event, based on the synthetic historical data corresponding to the prescription drug event;
• estimating, for the group type, an aggregated output based on the likelihood of a prescription drug event for the at least one user from the updated set of users;
• presenting the aggregated output via a display device, for the at least one user from the updated set of users;
• in response to a correlation between the prescription drug event and a second prescription drug event, computing a second likelihood of the second prescription drug event based on the synthetic historical data corresponding to the second prescription drug event;
• estimating, for the group type, the aggregated output based on the likelihood of the second prescription drug event;
• presenting the aggregated output via the display device, for the at least one user from the updated set of users, based on the likelihood of the second prescription drug event;
• computing a third likelihood of discontinuation of one or more drugs based on the synthetic historical data corresponding to the discontinuation, wherein the prescription drug event comprises the discontinuation;
• and
• computing a fourth likelihood of initiation of at least one drug based on the synthetic historical data corresponding to the initiation, wherein the second prescription drug event comprises the initiation.

A non-transitory, computer-readable medium having instructions thereon, which, when executed by a processor, perform a method comprising:

• in response to receiving a request indicating a group type and a time frame, by the processor communicatively coupled to a memory device,
• generating synthetic historical data, by:
• selecting a set of users from the plurality of users based on the group type;
• retrieving, for the plurality of users from the memory device, user data and historical data, to create retrieved user data and retrieved historical data;
• identifying a set of new users of the plurality of users during the time frame based on the retrieved user data and the retrieved historical data;
• adding the set of new users to the set of users, to generate an updated set of users;
• and
• generating the synthetic historical data for at least one user from the updated set of users;
• for the at least one user from the updated set of users, computing a likelihood of a prescription drug event, based on the synthetic historical data corresponding to the prescription drug event;
• estimating, for the group type, an aggregated output based on the likelihood of a prescription drug event for the at least one user from the updated set of users;
• presenting the aggregated output via a display device, for the at least one user from the updated set of users;
• in response to a correlation between the prescription drug event and a second prescription drug event, computing a second likelihood of the second prescription drug event based on the synthetic historical data corresponding to the second prescription drug event;
• estimating, for the group type, the aggregated output based on the likelihood of the second prescription drug event;
• presenting the aggregated output via the display device, for the at least one user from the updated set of users, based on the likelihood of the second prescription drug event;
• computing a third likelihood of discontinuation of one or more drugs based on the synthetic historical data corresponding to the discontinuation, wherein the prescription drug event comprises the discontinuation;
• and
• computing a fourth likelihood of initiation of at least one drug based on the synthetic historical data corresponding to the initiation, wherein the second prescription drug event comprises the initiation.