Abstract: Systems and methods for automated data quality semantic constraint identification using rich data type inferences are disclosed. In one embodiment, a method for automated data quality analysis may include: (1) receiving, by a data quality engine computer program, reference data from a data source, wherein the reference data comprises a plurality of columns; (2) inferring, by the data quality engine computer program, a rich data type for each of the plurality of columns, wherein the rich data type has a specific format, a content constraint, and/or a specific application; (3) applying, by the data quality engine computer program, a data quality constraint to each column based on the rich data type for the column; (4) updating, by the data quality engine computer program, the reference data with production data; and (5) identifying, by the data quality engine computer program, a data quality issue in the production data.

Abstract: Various methods, apparatuses/systems, and media for implementing a payment application module for searching billets are disclosed. A plurality of data sources include customer profile data, customer payment history data, biller information data, and biller directory data. A processor operatively coupled to the plurality of data sources via a communication network builds a customer profile service area popularity model based on the customer profile data, customer payment history data, biller information data, and biller directory data; receives search query data for searching a biller; builds a biller search machine learning model to optimize weights applied to the search query data; and ranks search results by utilizing the machine learning model in response to the search query data.

Abstract: Systems and methods for automated data quality semantic constraint identification using rich data type inferences are disclosed. In one embodiment, a method for automated data quality analysis may include: (1) receiving, by a data quality engine computer program, reference data from a data source, wherein the reference data comprises a plurality of columns; (2) inferring, by the data quality engine computer program, a rich data type for each of the plurality of columns, wherein the rich data type has a specific format, a content constraint, and/or a specific application; (3) applying, by the data quality engine computer program, a data quality constraint to each column based on the rich data type for the column; (4) updating, by the data quality engine computer program, the reference data with production data; and (5) identifying, by the data quality engine computer program, a data quality issue in the production data.

Abstract: Various methods, apparatuses/systems, and media for implementing a payment application module for searching billets are disclosed. A plurality of data sources include customer profile data, customer payment history data, biller information data, and biller directory data. A processor operatively coupled to the plurality of data sources via a communication network builds a customer profile service area popularity model based on the customer profile data, customer payment history data, biller information data, and biller directory data; receives search query data for searching a biller; builds a biller search machine learning model to optimize weights applied to the search query data; and ranks search results by utilizing the machine learning model in response to the search query data.