|
Objectives
At the end of the courses the students are expected to have basic knowledge about:
·risks and opportunities associated with big data
·analytical, computational, and algorithmic know-how of how to make the often hidden information in big data visible
·how to visualize, represent, analyze, quantify, and model complex dynamical processes via big data analytics and thereby build predictive knowledge about the system at hand.
In addition, the students will have ample opportunity to gain hands-on experience in handling, analyzing and making sense out of big data.
Target Attendees / Participants
The course is dedicated to university students of Steinbeis European Master Program in Risk Engineering and Management, and similar programs.
Course Content by Units
The module will cover the following courses:
Complex System Theory
Facing ever-growing amounts of data brings about the challenge to transform this data into actionable knowledge. This course provides theoretical, computational, and algorithmic frameworks that are often summarized under the term “Complex System Theory”. The course will outline several different approaches to make complex and high-dimensional datasets accessible and amenable for visualization and further analysis, including network theory, statistics of strongly correlated systems, and the analysis of complex dynamical processes. With this equipped, we will understand why complex systems often introduce a new type of risk that is called “systemic risk”, namely the risk that an entire system will break down or cease functioning as a result of an initially relatively minor default or error.
Managing Risk in Complex Systems
As the recent financial crisis that started in 2008 has shown, we do neither understand nor know how to deal with systemic risk, that is the risk that an entire system will break down or cease functioning due to initially relatively minor defects. The course introduces a quantitative framework to understand under which circumstances the increasing complexity and interconnections of socio-economic and environmental systems leave them more vulnerable to small risks that may trigger a possibly complex chain of events leading to consequences at much higher levels of organization. We will learn how to quantify the systemic risk in different types of complex system and how it can be managed in a data-driven way. This will be shown on various real-word examples, including financial markets, commodity trade, and health care
Practical Example: Workshop Big Data
The course will cover several examples of where and how analytics of big data can be used to identify, understand and quantify novel types of risk or novel risk-risk interconnections. These example will cover natural language processing techniques to cluster large collections of unstructured data and its application in the detection of risk-risk interdependencies, mining social media in order to assess the impact and response to, both, endogenous and exogenous shocks, or how big and open datasets can be used to identify risks as well as opportunities in various contexts, for example for economic growth or in the management of supply chains. The course will also provide an overview of the methodological know-how behind these examples. Since many of the datasets for the discussed examples are available for free, the students will have the opportunity to repeat the analyses and gain hands-on experience.
Teaching Methods
The module
is illustrated by number of examples,
presents commonly used methods and tools,
and provides exercises and preparation for the final exam.
Literature
1. M. E. J. Newman, Networks - An Introduction, Oxford University Press (2010)
2. M. O. Jackson, Social and Economic Networks, Princeton University Press (2008)
3. J.H. Holland, Hidden Order: How Adaptation Builds Complexity, Perseus Books (1995).
4. S.A. Kauffman: The Origins of Order. New York (1993).
5. A.G. Haldane, R.M. May, Nature 469, 351-5 (2011).
6. S. Battiston, M. Puliga, R. Kaushik, P. Tasca, G. Caldarelli, Sci. Rep. 2, 541 (2012).
7. S. Thurner, S. Poledna, Sci. Rep. 3, 1888 (2013).
8. C.A.Hidalgo, B.Klinger, A.-L. Barabási, R. Hausmann, Science 317, 482 (2007)
9. C.A. Hidalgo, R. Hausmann, PNAS 106(26), 10570 (2009)
10. P. Klimek, W. Bayer, and S. Thurner, Physica A 390, 3870-3875, (2011)
11. R. Crane, F. Schweitzer, D. Sornette, Phys. Rev. E, 81 (2010), 5, 056101.
12. P.S. Dodds, K. Harris, I. Kloumann, C. Bliss, C. Danforth PLoS ONE 2011, 6(12): e26752.
|