Big data based predictive graph generation system

A method, comprising:

• receiving, by a predictive graph processing platform, information stored in a data repository, wherein the information is stored in the data repository by a data accumulation service and is updated in near real time;
• updating the data stored in the data repository into an updated data set based on identification of a change to data at a data source of a plurality of data sources, wherein the plurality of data sources comprises a social media network;
• transforming the information received from the data repository into a predictive graph data set based on a predictive model, wherein the predictive model comprises one of a static model or a dynamic model;
• predicting, based the updated data set, at least a first semantic relationship between a plurality of objects of the updated data set using the predictive model;
• storing the predictive graph data set to a visualization data repository, wherein the predictive graph data set comprises a vertices table and an edge table and wherein each edge stored in edge table represents a semantic relationship between two vertices;
• generating a predictive graph visualization for presentation at a user device in response to a request received at the predictive graph processing system;
• and
• communicating the predictive graph visualization to a display device for display to a user;
• and
• receiving, via an input device, an input from a user corresponding to user interaction with the predictive graph visualization comprising one of a desired action to be performed based on the predictive graph data set or an update to the predictive graph data set.

Non-transitory computer readable media, storing instructions that, when executed by a processor, cause a computing device to:

• receive information from a plurality of data sources, wherein the plurality of data sources comprises two or more of business computing systems, social media networks, and user devices;
• store the information received from the plurality of data sources in a data repository;
• monitor the plurality of data sources for at least one data change event at one or more of the plurality of data sources;
• update, based on the data change event, the data stored in the data repository into an updated data set;
• transform, based on a predictive model, the information retrieved from the data repository into a predictive graph data set;
• predict, based on an indication of the data change event and using the predictive model, a first relationship between a plurality of objects of an updated data set, wherein the first relationship between the plurality of objects of the updated data set comprises a semantic relationship;
• store the predictive graph data set to a visualization data repository, wherein the predictive graph data set comprises the first relationship;
• and
• cause display, based on a visualization request, a visualization of the predictive graph data set comprising an indication of the first relationship between the plurality of objects of the updated data set.