Navigating the Data Science Frontier: Unveiling the Life Cycle, Algorithms, Challenges, and Future Prospects

Abstract

Recently data science has been identified as one of the most motivating research areas. The data science life cycle begins with data collection, data preparation, data model planning, model building, and then implementations. In this chapter, the authors focus on data preparation, data science algorithm, and their comparison. Data science algorithms utilize machine learning and deep learning algorithms to extract unknown knowledge and pattern from the data. Data scientists mainly suffers challenges such as heterogeneous data, overfitting/underfitting, imbalanced data, real-time data, and security during model building. Storage and extracting real-time data is a challenging task for any data scientist. Hence, the foremost future research trends will indicate extracting and storing real-time stream data, which require innovative ways to develop, explain, and justify the algorithms.