Machine learning classifier and prediction engine for artificial intelligence optimized prospect determination on win/loss classification

A method being performed by a computer system that comprises one or more processors, a memory operatively coupled to at least one of the processors, and a computer-readable storage medium encoded with instructions executable by at least one of the processors and operatively coupled to at least one of the processors, the method comprising:

• receiving into memory a company engagement database comprising a list of company engagements for a client user, wherein the list comprises won company engagements;
• compiling a training database comprising training data comprising
• company entity data linked to each company in the list, the company entity data comprising firmographic data from a business entity information database;
• and
• non-customer company data from the business entity information database, the non-customer company data comprising company engagement data for the non-customer company, and company entity data linked to each non-customer company engagement, wherein the non-customer company engagement includes non-company won engagements, the non-customer company entity data comprising the firmographic data from the business entity information database, wherein the non-customer company engagement data including the won engagements is mapped to the company engagement data for the client user;
• training at least one classifier on the training data in the training database to train the at least one classifier to identify one or more attractive classes and one or more unattractive classes to classify company prospects;
• outputting the at least one classifier to a classification engine;
• running the at least one classifier on a database comprising the company entity data and the firmographic data to identify prospect companies classified as attractive;
• and
• outputting a database of company prospects to a client user interface.

A computer program product including non-transitory computer readable memory encoded with instructions executable by a computer system that, when executed by at least one processor of the computer system, performs the method comprising:

• receiving into a memory a company engagement database comprising a list of company engagements for a client user, wherein the list comprises client won company engagements;
• compiling a training database comprising training data comprising
• company entity data linked to each company, the company entity data comprising firmographic data from a business entity information database, and
• non-customer company data from the business entity information database, the non-customer company data comprising non-customer company engagement data and company entity data linked to each company engagement, wherein the non-customer company engagements include non-company won engagements, the company entity data comprising the firmographic data from the business entity information database, wherein the non-customer company engagement data including the won engagements is mapped to the company engagement data including the client won engagements for the client user;
• training at least one classifier on the training data in the training database to train the at least one classifier to identify one or more attractive classes and one or more unattractive classes to classify company prospects;
• outputting the at least one classifier to a classification engine;
• running the at least one classifier on a database comprising the company entity data and the firmographic data to identify prospect companies classified as attractive;
• and
• outputting a database of company prospects to a client user interface.