Self-adaptive, self-trained computer engines based on machine learning and methods of use thereof

1. A computer system, comprising:

a plurality of electronic content feeds from a plurality of distinct electronic sources;

at least one content database that is configured to store at least initial content data derived from the plurality of electronic content feeds;

a non-transient memory, storing particular program code; and

at least one computer processor that, when executing the particular program code, is configured to:

obtain at least one portion of the initial content data from the at least one content database;

apply at least one machine learning model to transform the at least one portion of the initial content data into a N-dimensional vector space;

apply at least one clustering technique to the N-dimensional vector space to generate a cluster model that defines a plurality of vector clusters;

obtain at least one portion of first subsequent content data from the at least one content database;

wherein the first subsequent content data is content data received from the plurality of electronic content feeds from the plurality of distinct electronic sources after the cluster model has been generated during at least one first time period;

associate each data element of at least one portion of the first subsequent content data with each respective vector cluster of the plurality of vector clusters of the cluster model to generate a content data cluster mapping model;

continuously track, in real-time, activity of each respective user regarding at least one data element from at least one respective portion of the first subsequent content data during each respective time period to form a plurality of respective continuously self-adapting user-specific, time-specific dynamic cluster mapping models;

and

automatically provide, to each respective user, based, at least in part, on each respective continuously self-adapting user-specific, time-specific dynamic cluster mapping model, at least one relevant subscription recommendation regarding at least one recommended content feed without a need that each respective user is to take an action that would identify a desire by each respect user to be subscribed to the at least one content feed.

2. The computer system of claim 1 , wherein the at least one computer processor, when executing the particular program code, is further configured to:

apply each respective continuously self-adapting user-specific, time-specific dynamic cluster mapping model to at least one portion of second content data obtained during at least one second time period to determine a user-specific output content data to be delivered to each respective user at a particular time period.

3. The computer system of claim 1 , wherein the at least one computer processor is further configured to:

update, for each user, each respective continuously self-adapting user-specific, time-specific dynamic cluster mapping model based, at least in part, on at least one of:

i) at least one biological feature of each respective user,

ii) at least one social feature of each respective user,

iii) at least one economic feature of each respective user,

iv) at least one behavioral feature of each respective user, and

v) any combination thereof.

4. The computer system of claim 1 , wherein the at least one machine learning model is Doc2Vec model.

5. The computer system of claim 1 , wherein the at least one recommended content feed is at least one of:

i) at least one educational information feed,

ii) at least one recommendation feed,

iii) at least one feed with mobile applications-related information, or

iv) at least one feed with trading-related information, or

v) at least one news feed.

6. The computer system of claim 5 , wherein the at least one computer processor is further configured to perform:

cause to deliver at least one portion of the at least one recommended content feed to at least one portable electronic device of each respective user.

7. A computer-implemented method, comprising:

obtaining, by at least one processor, at least one portion of initial content data from at least one content database;

wherein the at least one content database comprises the initial content data derived from a plurality of electronic content feeds from a plurality of distinct electronic sources;

applying, by the at least one processor, at least one machine learning model to transform the at least one portion of the initial content data into a N-dimensional vector space;

applying, by the at least one processor, at least one clustering technique to the N-dimensional vector space to generate a cluster model that defines a plurality of vector clusters;

obtaining, by the at least one processor, at least one portion of first subsequent content data from the at least one content database;

wherein the first subsequent content data is content data received from the plurality of electronic content feeds from the plurality of distinct electronic sources after the cluster model has been generated during at least one first time period;

associating, by the at least one processor, each data element of at least one portion of the first subsequent content data with each respective vector cluster of the plurality of vector clusters of the cluster model to generate a content data cluster mapping model;

continuously tracking, for each user, in real-time, by the at least one processor, activity of each respective user regarding at least one data element from at least one respective portion of the first subsequent content data during each respective time period to form a plurality of respective continuously self-adapting user-specific, time-specific dynamic cluster mapping model; and

automatically providing, by the at least one processor, to each respective user, based, at least in part, on each respective continuously self-adapting user-specific, time-specific dynamic cluster mapping model, at least one relevant subscription recommendation regarding at least one recommended content feed without a need that each respective user is to take an action that would identify a desire by each respect user to be subscribed to the at least one recommended content feed.

8. The computer-implemented method of claim 7 , further comprising:

applying, by the at least one processor, each respective continuously self-adapting user-specific, time-specific dynamic cluster mapping model to at least one portion of second content data obtained during at least one second time period to determine a user-specific output content data to be delivered to each respective user at a particular time period.

9. The computer-implemented method of claim 7 , wherein the method further comprises:

updating, for each user, by the at least one processor, each respective continuously self-adapting user-specific, time-specific dynamic cluster mapping model based, at least in part, on at least one of:

i) at least one biological feature of each respective user,

ii) at least one social feature of each respective user,

iii) at least one economic feature of each respective user,

iv) at least one behavioral feature of each respective user, and

v) any combination thereof.

10. The computer system of claim 7 , wherein the at least one machine learning model is Doc2Vec model.

11. The computer-implemented method of claim 7 , wherein the at least one recommended content feed is at least one of:

i) at least one educational information feed,

ii) at least one recommendation feed,

iii) at least one feed with mobile applications-related information, or

iv) at least one feed with trading-related information, or

v) at least one news feed.

12. The computer-implemented method of claim 7 , further comprising:

causing, by the at least one processor, to deliver at least one portion of the at least one recommended content feed to at least one portable electronic device of each respective user.