Data science refers to the employment of methods for analyzing voluminous amount of data and extracting the knowledge encompassed within. Big data, on the other hand, is an extensive term for any collection of large datasets, usually with those of billions of values. They are so large or complex that it becomes a challenge to process them by employing conventional or traditional techniques of data management. The relationship between data science and big data bears resemblance that of raw material and manufacturing plant [Karaca, Y., & Cattani, C. (2018)]. The properties of big data are referred to volume (how much data there are), variety (how diverse the different types of data are), velocity (how fast new data are generated) as well as veracity (how accurate the data are) [Warren, J., & Marz, N. (2015)].
Data science as a broad interdisciplinary field utilizes methods, algorithms, processes and systems for the extraction, manipulation and analysis of information from big data, structured or unstructured data, mixed data, and so forth. Data science lifecycle refers to the different stages a project goes through from the first stage of conception to data collection, later communicating results and insights. Handling complex data, data collection and storage, experimentation, prediction, making accurate conclusions and data-driven decisions are among the important steps within this process. The significance of data science lies in the advances encountered in digital technologies which have brought about explosion of data and value creation which goes beyond the analysis of data including the important stages of interpreting and using the data to be capable of making informed decisions, predicting future trends, providing sustainability and maintaining efficiency.
Among the disciplines interacting with data science are modern statistics which with its novel and powerful techniques in modern statistics as well as machine learning algorithms are required for supporting diverse applications. Information and decision theory comprises research in optimization, game theory, systems and controls along with networks, inference and data processing. From data to decisions, it has become inevitable to identify models for decision-making by taking into consideration the diversity, magnitude, diversity and structure of modern datasets that pose new challenges around how to use them. Under the ever-evolving conditions which also apply to the evolving nature of data, it is essential that one address issues of privacy, security and data integrity as new means are designed and developed for the exploration of big datasets and models and eventually for being able to make better decisions. For other related details, you may kindly refer to...
Seminars
Articles
Contact