Automated Business Goal Extraction from E-mail Repositories to Bootstrap Business Understanding

The Cross-Industry Standard Process for Data Mining (CRISP-DM), despite being the most popular data mining process more than two decades, is known to leave those organizations lacking operational experience puzzled and unable start their projects. This especially apparent in first phase of Business Understanding, at conclusion which, goals project hand should be specified, which arguably requires least a conceptual understanding knowledge discovery process. We propose bridge this gap from Science perspective by applying Natural Language Processing techniques (NLP) organizations’ e-mail exchange repositories extract explicitly stated business conversations, thus bootstrapping Understanding CRISP-DM. Our NLP-Automated Method (NAMBU) generates list can subsequently used further specification goals. validation results on basis comparison manual goal extraction Enron corpus demonstrates usefulness our NAMBU method when applied large datasets.