The Components

In the previous article we defined data science, and now it is time to look closer at the details of its components.

Big data

In data science we rely on the data that exists in order to understand the world around us. It is difficult to make a decision based only on internal data. Therefore, the data in data science consists of data that comes from internal organizational sources as well as the external environment.

Techniques and Algorithms

Once we have access to big data in order to study a phenomenon or make a decision, we will then need to select the most appropriate analytics algorithms to use. For example, predictions might need a regression model whereas classification needs classifier algorithms such as decision trees or neural networks.

Process

In order to be able to reduce the risks of data science projects and govern the activities conducted and the big data used, we must follow a structured process. The process should be able to cover an end-to-end scope and provide tools and activities in order to safeguard the data science project. In this course, we discuss some processes and we have chosen to focus on one called the CRISP-DM, as it is the most frequently used one.

Knowledge

The knowledge we obtain by running analytics algorithms on big data and following a structures process will help us better understand the problem and phenomenon necessary to solve challenges.

Decisions

The knowledge we have obtained contribute to better understanding and accordingly better and informed data-driven decisions. The ability to make data-driven decisions influence the fate of organizations and society at large.

More about each of these topics will be discussed and explained further throughout the course activities.