Kelleher John D. | Tierney Brendan: Znanost o podacima

John D. Kelleher, Brendan Tierney: Data Science

Data science encompasses a set of principles, problem definitions, algorithms, and processes for extracting fuzzy and useful patterns from big data (Big Data) with the goal of improving decision making based on big data insights. As a field of practice, data science encompasses a set of principles, problem definitions, algorithms, and processes for extracting non-obvious but useful patterns of data behavior from big data. It is closely related to the fields of data mining and machine learning, but is broader in scope.

Today, data science governs decision-making in almost all parts of modern societies. Some of the ways in which data science can affect your daily life include, among others: the choice of advertisements that are offered to you through virtual advertising; they are recommendations for movies you should see, books you should read, and friendships you should make; suggestions on which emails to put in the spam folder; benefits that will be offered to you when renewing your subscription to the mobile phone service; the price quote for the health insurance premium offered to you; placement and dynamics of traffic lights in your area; the composition of the medicines you need; as well as what places in your city the police are lurking.

The aim of this book is to provide an introduction to data science that covers its essential achievements, to a level that provides a principled understanding of the field.

The first chapter introduces the field of data science and provides a brief overview of its development. It also explains why data science is important today and lists some of the factors influencing its adoption.

The second chapter introduces fundamental concepts related to data itself. It also describes the standard stages of implementing data science projects: business understanding, data understanding, data preparation, modeling, evaluation and implementation.

The third chapter describes the typical infrastructure of organizations, established for the needs of data science, as well as some modern solutions related to the problem of circulating large data sets within the data infrastructure, which include the use of machine learning integrated with the database, the use of the Hadoop system for data storage and processing, and the development of hybrid database systems that smoothly combine traditional database software solutions and similar solutions to Hadoop.

Chapter four introduces the field of machine learning and explains some of the most popular machine learning algorithms and models, including neural networks, deep learning models, and decision tree models.

Chapter five focuses on connecting machine learning domain expertise to real-world problems, presenting a series of standard business problems and describing how they can be solved using machine learning.

Chapter six considers the ethical implications of data science, the latest developments in legal regulation in that area, as well as some new computational approaches to preserving the privacy of individuals in processes related to big data.

Finally, the seventh chapter describes some of the areas in which data science will have a significant impact in the near future and sets out some of the principles that are important for whether a project within its reach will be successful or not.