Objectives: Data-driven decisions are changing the way organizations (and science) operate. Relying on increasingly available large amounts of data organizations leverage quantitative analytics for their operations. Data, however, is growing in volume, velocity (time sensitivity), variety, and veracity requiring novel approaches for analytics and new capabilities for decisions makers to master this avalanche of data. The goal of this course is to learn about the architecture and programming models of massive parallel data processing systems used in industry today. You will learn how they work without having to understand the details of their technical implementation. We will cover the architecture of these systems and their trade-offs on an abstract level but also provide pointers to more detailed explanations.. This course will enable you to leverage massive parallel computing systems to write basic big data analysis applications using the system API's and high level libraries and prepare you for other, more technically-oriented resources that you may encounter when working with these systems.
Teaching Format: The course consists of one lecture every week and integrated into the lecture are practical exercises.
Evaluation: There is a written final exam graded from 1 to 6 with quarter grades. The final exam will take place on 18 June 2019.
OLAT: All course-related information (lecture slides, practical exercises, etc.) is published on the corresponding OLAT course page.