Exploring the Big Data and Machine Learning Framing Concepts for a Predictive Classification Model

摘要

Understanding big data and machine learning framing concepts to develop a predictive classification model was essential for the growth and evolution of data science and other industries. Many data scientists conducted extensive research in the area of big data and machine learning to develop predictive classification models. In 2017, data scientists created predictive models by using models that solely featured text or only with images. However, this study presents for the first time, the big data and machine learning framing concepts needed to develop a predictive classification model to combine images and text to improve the predictive classification for 2D, gray-scale images such as dental application and text such as the patient medical history. In this study, framing concepts are a list of requirements, processes, tools, and common best practices. The study identified 16 major themes related to the big data and machine learning framing concepts, 17 more themes to support the architecture, and 8 themes related to the future of big data and machine learning to improve the predictive classification for 2D, gray-scale images and text. The big data and machine learning framing concepts presented in this study will allow future researchers to develop predictive classification models to assist doctors to use images and patient data for diagnosis, to assist criminal investigators in utilizing images and investigations notes or reports, airplane or vehicle accidents investigations, general manufacturing, retail industry, big data analytics, and many other fields. The research methodology used in this study was qualitative research. Nine experienced professionals participated in the study.