Data discovery, visualization, and advanced analytics system and method

An Artificial Intelligence (AI) based data analytical method, for one or more industry sectors comprising:

• receiving, by at least one hardware processor, database authentication information from a client computing device, wherein upon receiving the database authentication information one or more security configurations are initialized, including the one or more security configurations associated with Lightweight Directory Access Protocol (LDAP), custom credentials, and external security options;
• continually obtaining, by the at least one hardware processor, data from a first data source using the database authentication information, the first data source storing data having a first representation of the data;
• continually converting and storing, by the at least one hardware processor, the data in a second data source in real-time as the data is received in the first data source, the second data source having a second representation of the data that is different from the first representation of the data, wherein the second representation of the data comprises at least one of:
• a hypercube and an offset cube, wherein the offset cube is used to manage big data by performing aggregation on-the-fly during data ingestion into a connected database, thereby eliminating a need for regeneration or reloading of cubes upon arrival of new data, wherein a directed acyclic graph (DAG) governs, cleans, and builds a pipeline for aggregation on-the-fly for the new data, wherein a system is configured to interrogate data on-the-fly through optimization of the offset cube;
• receiving, by the at least one hardware processor, a selection of at least one machine learning algorithm from a customizable library of machine learning algorithms, including a subset of favorite machine learning algorithms, wherein the at least one machine learning algorithm is selected, dragged and dropped into the pipeline within an end-to-end no-code data to insight platform, and add at least one of the favorite machine learning algorithms to a template to perform at least one operation on the data in the second data source, wherein the customizable library of machine learning algorithms comprises at least one of one or more:
• artificial intelligence (AI) models, deep learning (DL) algorithms, and natural language processing (NLP) algorithms;
• receiving, by the at least one hardware processor, a request to create a visualization of the data and generating a visualization of the data using the second representation of the data based on the at least one machine learning algorithm;
• determining, by the at least one hardware processor, recommendations for created visualizations of the data through a generative AI enabled recommendation engine, wherein the generative AI enabled recommendation engine is configured to generate a natural language interpretation of output of the at least one machine learning algorithm to guide user decision making;
• and
• transmitting, by the at least one hardware processor, the visualization and recommendations of the data to the client computing device.

A non-transitory computer-readable storage medium, having instructions stored thereon that, when executed by a computing device cause the computing device to perform operations, the operations comprising:

• receiving database authentication information from a client computing device, wherein upon receiving the database authentication information one or more security configurations are initialized, including the one or more security configurations associated with Lightweight Directory Access Protocol (LDAP), custom credentials, and external security options;
• continually obtaining data from a first data source using the database authentication information, the first data source storing data having a first representation of the data;
• continually converting and storing the data in a second data source in real-time as the data is received in the first data source, the second data source having a second representation of the data that is different from the first representation of the data, wherein the second representation of the data comprises at least one of:
• a hypercube and an offset cube, wherein the offset cube is used to manage big data by performing aggregation on-the-fly during data ingestion into a connected database, thereby eliminating a need for regeneration or reloading of cubes upon arrival of new data, wherein a directed acyclic graph (DAG) governs, cleans, and builds a pipeline for aggregation on-the-fly for the new data, wherein a system is configured to interrogate the data on-the-fly through optimization of the offset cube;
• receiving a selection of at least one machine learning algorithm from a customizable library of machine learning algorithms, including a subset of favorite machine learning algorithms,
• wherein the at least one machine learning algorithm is selected, dragged and dropped into the pipeline within an end-to-end no-code data to insight platform, and add at least one of the favorite machine learning algorithms to a template to perform at least one operation on the data in the second data source, wherein the customizable library of machine learning algorithms comprises at least one of one or more:
• artificial intelligence (AI) models, deep learning (DL) algorithms, and natural language processing (NLP) algorithms;
• receiving a request to create a visualization of the data and generating a visualization of the data using the second representation of the data based on the at least one machine learning algorithm;
• determining recommendations for created visualizations of the data through a generative AI enabled recommendation engine, wherein the generative AI enabled recommendation engine is configured to generate a natural language interpretation of output of the at least one machine learning algorithm to guide user decision making;
• and
• transmitting the visualization and recommendations of the data to the client computing device.