Methods and systems for self-tuning personalization engines in near real-time

A computer implemented method for providing personalization of a website's new content to a user interacting with the website's existing content, comprising:

• receiving data (i) representative of the user's interaction with the existing content presented on the website and (ii) indicative of content entities of interest to the user;
• storing the received data indicative of the content entities of interest and disinterest as nodes in a graph database;
• analyzing, via a plurality of personalization engines, each of which uses machine learning analytics, a plurality of relations between a first node and a second node;
• wherein each analyzed relation creates a respective link, a structure of the respective link being a function of the user's interaction with the existing content, wherein each respective link contains a plurality of personalization links relating the first node to the second node and wherein each of the plurality of personalization links are associated with one or more of the plurality of personalization engines;
• and
• personalizing, via the processors, the website's new content for presentation to the user,
• wherein a first personalization engine captures instant explicit and implicit interactions and implicit behaviors and a second personalization engine captures provides intra-session and extra-session personalization user actions;
• wherein a portion of the new content is (i) derived from the respective link and (ii) delivered to the user online and in real time when a type of the respective link is within a first category
• wherein when the type of the link is within a second category, the personalizing of the website's new content to the user occurs off-line;
• wherein the structure includes a numerical value corresponding to a relative weight of the of the user's level of interest in the respective link;
• and
• when the user ceases to interact with content over time, one of the plurality of personalization engines will detect a diminished level of activity and will adjust the relative weight of the user's level of interest in the respective link.

A non-transitory computer-readable medium having stored thereon, computer executable instructions that, if executed by a computing device, cause the computing device to perform a method for providing personalization of a website's new content to a user interacting with the website's existing content, comprising:

• receiving data (i) representative of the user's interaction with the existing content presented on the website and (ii) indicative of content entities of interest to the user;
• storing the received data indicative of the content entities of interest as nodes in a graph database;
• analyzing, via a plurality of personalization engines, each of which uses machine learning analytics, a plurality of relations between a first node and a second node;
• wherein each analyzed relation creates a respective link, a structure of the respective link being a function of the user's interaction with the existing content, wherein each respective link contains a plurality of personalization links relating the first node to the second node and wherein each of the plurality of personalization links are associated with one or more of the plurality of personalization engines;
• and
• personalizing, via the processors, the website's new content for presentation to the user, wherein a first personalization engine captures instant explicit interactions and implicit behaviors and a second personalization engine provides intra-session and extra-session personalization;
• wherein a portion of the new content is (i) derived from the respective link and (ii) delivered to the user online and in real time when a type of the respective link is within a first category;
• wherein when the type of the link is within a second category, the personalizing of the website's new content to the user occurs off-line;
• wherein the structure includes a numerical value corresponding to a relative weight of the of the user's level of interest in the respective link;
• and
• when the user ceases to interact with content over time, one of the plurality of personalization engines will detect a diminished level of activity and will adjust the relative weight of the user's level of interest in the respective link.