From a collection of "fancy" approaches that could "also" be applied, the area of data science (DS) has developed into a set of well-founded methodologies to address challenging problems in a variety of fields, including science, engineering and technology, economics, and science. Data Science is widely applicable to a broad range of issues due to its universality, which has been fostered by the synergistic relationship between theory and practice.
Machine learning algorithms, optimization, decision theory, and statistical learning theory are the theoretical cornerstones of Data Science. The performance of DS techniques is ensured when they are scaled across other problem domains because to this basic framework. Every new application domain that DS methods are utilized to presents theorists with fresh difficulties. Because of this, a number of DS features that theorists are currently interested in are primarily anchored in different application areas. These include (but are not limited to) privacy, security, sample efficiency, transfer learning, fairness, and interpretability. Novel developments in systems are crucial due to the growing complexity and computing demands of data-heavy models and techniques. This provides the fundamental understanding needed to apply the solutions effectively.