Commentary

Course Objective

Graphs (and the related concept of Networks) have emerged from a relative mathematical and physics niches to become mainstream models for describing and interpreting various phenomena. The objective of the course is to review various important graph types as they are increasingly explored in data science and sketch their linkages and relationships (a graph of graphs!).

Data Types are a fundamental building block of data science

Data science is about data, but data are not simple and tame beasts. They have character and attitude, which can cause a lot of friction between them and the data scientist. There is a lot of sweat and tears involved when confronting data, but data scientists can do worse than know how to handle in particular Data Type quirks. Namely, a good fraction of data science involves not modelling data, not transforming data, not even cleaning data but simply goading data around the right containers, providing them with the right stage that fits their character. Getting the data type wrong is many a source of both spectacular bugs and hidden, insidious application errors.

What is the future of stress testing?

To speculate on the future of Stress Testing we need first a basic definition what stress testing is. Broadly speaking, the goal of Stress Testing is to assess how a system would behave under adverse conditions that - while not the most likely outcome with the knowledge of today - are within the realm of the plausible.

Introduction

What is FOSDEM?

FOSDEM is a non-commercial, volunteer-organized event centered on free and open-source software development (with a geographic focus on the European open source ecosystems / projects). FOSDEM is aimed at developers and anyone interested in the free and open-source software movement. It aims to enable developers to meet and to promote the awareness and use of free and open-source software.

Risk, Randomness, Uncertainty and other Ambiguous Terms

Uncertainty versus Risk is a popular discussion topic among risk managers, especially after major risk management disasters. The debate can get really hairy and drift into deep philosophical areas about the nature of knowledge etc. Yet the significance of having an as clear as possible language toolkit around these terms should not be underestimated. Practical risk management typically shuns too deep excursions into the meaning of things, yet that is not quite compatible with the use of sophisticated methods and tools (such as a Risk Model ) that assumes an understanding of the scope and limitations of “knowledge”.

Is the size of global debt truly “astronomical”?

The notion of astronomical numbers and figures is quite frequently seeping in everyday language when large quantities of something are encountered in “normal” life. The strict definition of astronomical is obviously something of, or relating to, astronomy and astronomical observations but in common usage it also denotes something enormously or inconceivably large. This is, of course, because astronomical figures are inconceivably large!

The role of simulation in risk management and decision support

A Simulation is a simplified imitation of a process or system that represents with some fidelity its operation over time. In the context of risk management and decision support simulation can be a very powerful tool as it allows us to assess potential outcomes in a systematic way and explore what-if questions in ways that might otherwise be not feasible. Simulation is used when the underlying model is too complex to yield explicit analytic models (An analytic model is one can be “solved” exactly or with standard numerical methods, for example resulting in a formula).

What is Risk Compensation?

Risk Compensation is a behavioral model of human attitudes towards risk which suggests that people might adjust their behavior in response to the perceived level of risk. It follows that, depending on the strength of the effect, that it might counteract and even annul the impact of risk mitigation, if the updated attitude and behavior modifies the actual underlying risk

Agent-Based Models

The origins and early years

According to Wikipedia an agent-based model (ABM) is

ABM: class of computational models for simulating the actions and interactions of autonomous agents (both individual or collective entities such as organizations or groups) with a view to assessing their effects on the system as a whole.

A survey of existing definitions of risk

When looking up the meaning of Risk we are confronted with a surprising situation. There is no satisfying and authoritative general purpose one-line definition that we can adopt without second thoughts. Let us start with the standard dictionary definitions:

What do people talk about at FOSDEM 2020

Introduction

FOSDEM is a non-commercial, volunteer-organized European event centered on free and open-source software development. It is aimed at developers and anyone interested in the free and open-source software movement. It aims to enable developers to meet and to promote the awareness and use of free and open-source software. FOSDEM is held annually since 2001, usually during the first weekend of February, at the Université Libre de Bruxelles Solbosch campus in the southeast of Brussels, Belgium. The history of FOSDEM is neatly available at Wikipedia, while the current conference (2020) website is available here.

What is a Risk Taxonomy?

There are various formal definitions of risk taxonomies (and we will go over those below), but it might be useful to first look at a very intuitive example of a risk taxonomy: the classification of fire hazards (also known as fire classes)

The new IFRS 9 financial reporting standard

IFRS 9 (and the closely related CECL) is a brand new financial reporting standard developed and approved by the International Accounting Standards Board (IASB).

Strictly speaking IFRS 9 concerns only the accounting and reporting of financial instruments (e.g. bank loans and similar credit products). Yet the introduction of the IFRS 9 standard has significant repercussions beyond financial reporting, and touches e.g., bank risk management as well. This is prompted by the fact that the framework requires embedding forward looking risk assessments in the measurement of the value of credit assets currently on the balance sheet.

Data Scientists Have No Future

The working definition of a Data Scientist seems to be in the current overheated environment:

doing whatever it takes to get the job done in a digital #tech domain that we have long neglected but which is now coming back to haunt us!

Four individuals that can look straight into your eyes

Here are four individuals that can look straight into your eyes

• Torvalds developed the #linux operating system, the software engine now powering anything from the tiniest #raspberrypi to the scariest supercomputer. Humanity’s best guarantee that the digital era remains an equal playing field
• Mullenweg developed the #wordpress blogging platform. Gave voice and content ownership to millions of digital authors making him the closest to the Gutenberg of our era
• Dougiamas developed #moodle, the world’s digital Academy. Capturing millenia of teacher’s experience into one powerful #elearning system makes him an educational innovator on a par with the Greek masters of antiquity
• Wales developed #wikipedia. It is not only the world’s digital encyclopedia and top 5 website. It is the most blinding evidence that tech enabled mass collaboration will change the human condition

They are all different characters from different walks of life. Yet they are united by the power of the #opensource software movement.

Machine Learning Ballyhoo

Are you getting a bit tired with all the machine learning ballyhoo?

You can blame it all on a German mathematician(*), Carl Friedrich Gauss, who started the futuristic mega-trend back in 1809: He showed us how to train a straight line to pass nicely through a cloud of unruly, scattered data points. To find, in effect, a path of least embarrassment.

If programming languages were human languages which one would be which?

Most developers know (or get to know quickly once they join a team) that programming languages are as much about communicating with other developers as they are about instructing the computer. Which raises the interesting question: If programming languages were human languages which one would be which? Here is a (tongue-in-cheek mind you!) compilation of a mapping between programming languages and human languages. Suggestions / corrections are welcome via the feedback button

The Zen of IFRS 9 Modeling

At Open Risk we are firm believers in balancing art and science when developing quantitative risk tools. The introduction of the IFRS 9 and CECL accounting frameworks for reporting credit sensitive financial instruments is a massive new worldwide initiative that relies in no small part on quantitative models. The scope and depth of the program in comparison with previous similar efforts (e.g. Basel II) suggests that much can go wrong and it will take considerable time, iterations, communication and training to develop a mature toolkit that is fit-for-purpose.

What are the guiding principles for a viable open source operational risk model (OSORM)? Such a framework should:

The Data Privacy genie is out of the bottle

From Yahoo’s massive email data leaks, to Equifax’s exposing of sensitive data for a large segment of the US population, to Apple’s resisting the bypassing the security features of the iPhone, not a week goes by without some alarming piece of news around data privacy.