Computing system learning of a merchant category code

A system for computing system learning of a merchant category code, the system comprising:

• a data repository for storing a plurality of merchant category codes;
• and
• a computer processor operably connected to the data repository and configured to execute a merchant category code predictor, the merchant category code predictor for causing the computer system to:
• access a social media platform using administrative information of a merchant to obtain social media information of the merchant;
• perform natural language processing on the social media information to add a first plurality of key terms to a first merchant terminology corpus defined for the merchant;
• normalize the first plurality of key terms in the first merchant terminology corpus;
• calculate, for each key term in the first merchant terminology corpus and for each merchant category code of the plurality of merchant category codes, a frequency value for the merchant category code to obtain a plurality of frequency values;
• aggregate the plurality of frequency values across the first plurality of key terms in the first merchant terminology corpus to obtain a plurality of aggregated values, the plurality of aggregated values comprising an aggregated value for the merchant and for each of at least a subset of the plurality of merchant category codes;
• select, using the plurality of aggregated values, the matching merchant category code for the merchant;
• and
• apply the matching merchant category code to the merchant.

A non-transitory computer readable medium for computing system learning of a merchant category code, the non-transitory computer readable medium comprising computer readable program code for:

• accessing a social media platform using administrative information of a merchant to obtain social media information of the merchant;
• performing natural language processing on the social media information to add a first plurality of key terms to a first merchant terminology corpus defined for the merchant;
• normalizing the first plurality of key terms in the first merchant terminology corpus;
• calculating, for each key term in the first merchant terminology corpus and for each merchant category code of a plurality of merchant category codes, a frequency value for the merchant category code to obtain a plurality of frequency values;
• aggregating the plurality of frequency values across the first plurality of key terms in the first merchant terminology corpus to obtain a plurality of aggregated values, the plurality of aggregated values comprising an aggregated value for the merchant and for each of at least a subset of the plurality of merchant category codes;
• select, using the plurality of aggregated values, the matching merchant category code for the merchant;
• and
• applying the matching merchant category code to the merchant.