SYSTEM AND METHOD FOR CLASSIFICATION OF UNSTRUCTURED DATA

The present disclosure provides a system, method, and computer program for modeling unstructured data. More specifically, a data modeling solution is provided that enables classification of values within unstructured data sources. The system, method, and computer program operate at a content level. This means that the content of unstructured data is analyzed to classify it. The system extracts information from the pool of unstructured data and classifies it for analysis. The system, method, and computer program maintain classification data types using a supervised machine learning process. Valid values are fed to the classification engine to add/update data constraints. This is an at least partially automated process for maintaining data types. Classification of data-including values, data type, class type, data class, and domain—may be saved to a data repository for further use by the system such that full classification need only be done once per value.