some output...

more work

The Alpha Engine: Designing an Automated Trading Algorithm

We introduce a new approach to algorithmic investment management that yields profitable automated trading strategies.

This trading model design is the result of a path of investigation that was chosen nearly three decades ago. Back then, a paradigm change was proposed for the way time is defined in financial markets, based on intrinsic events. This definition lead to the uncovering of a large set of scaling laws. An additional guiding principle was found by embedding the trading model construction in an agent-base framework, inspired by the study of complex systems.

This new approach to designing automated trading algorithms is a parsimonious method for building a new type of investment strategy that not only generates profits, but also provides liquidity and stability to financial markets and does not have a priori restrictions on the amount of assets that are managed.

Trading model simulations.

History

The trading model algorithm outlined here is the result of a long journey that began in the early 1980s. Starting with a new conceptual framework of time, this voyage set out to chart new terrain. The whole history of this endeavor is described in the appendix. The key ingredients of this new paradigm are:

• Intrinsic Time
• The Emergence of Scaling Laws (*)
• Trading Models and Complexity (*)
• Coastline Trading (*)
• Novel Insights from Information Theory
• The Final Pieces of the Puzzle: Asymmetric Thresholds

(* I was lucky to have been part of this 12-year leg of the journey)

The trading model algorithm described here is the result of a meandering journey that lasted for decades. Guided by an overarching event-based framework, recasting time as discrete and driven by activity, elements from complexity theory and  information theory were added. In a nutshell, the proposed trading model is defined by a set of simple rules executed at specific events in the market. This approach to designing automated trading models yields an algorithm that fulfills many desired

features. Its parsimonious, modular, and self-similar design results in behaviour that is profitable, robust, and adaptive.

⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼

Download the paper from SSRN

Download the code from GitHub

⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼⎼

Context

A crucial feature of the trading model is that it is designed to be counter trend. The coastline trading ensures that positions, which are going against a trend, are maintained or increased. In this sense, the models provide liquidity to the market. When market participants want to sell, the investment strategy will buy and vice versa. This market-stabilizing feature of the model is beneficial to the markets as a whole. The more such strategies are implemented, the less we expect to see runaway markets but healthier market conditions overall. By construction, the trading model only ceases to perform in low-volatility markets.

If investment strategies contribute to market liquidity, they can help stabilize prices and reduce the uncertainty in financial markets and the economy at large. For such strategies the investment returns can be viewed as a payoff for the value-added provided to the economy.

Your Help is Needed

In essence, what we present here is a proof of concept. We refrained from tweaking the model to yield better performance, in order to clearly establish and outline the model's building blocks and fundamental behavior. We strongly believe there is great potential for obvious and straightforward improvements,  which would give rise to far better models. Nevertheless, the bare-bones model we present here already has the capability of being implemented as a robust and profitable trading model that can be run in real-time. 

Nevertheless, with all the merits of the trading algorithm presented here, we are only at the beginning. The Alpha Engine should be understood as a prototype. The model can easily be improved by calibrating the various exchange rates by volatility, or by excluding illiquid ones. Furthermore, the model treats all the currency pairs in isolation. There should be a large window of opportunity for increasing the performance of the trading model by introducing correlation across currency pairs. This is a unique and invaluable source of information not yet exploited. Finally, a whole layer of risk management can be implemented on top of the models.

We hope to have presented a convincing set of tools motivated by a consistent philosophy. If so, we invite the reader to take what is outlined here and improve upon it...

--

This paper will appear as a chapter in the book High Performance Computing in Finance: Problems,  Methods, and Solutions, Chapman & Hall/CRC Series in Mathematical Finance, 2017

More Networks

at work

This is a network of power. This time not economic power, but megawatts of capacity.

The pink nodes are power plants producing energy. They are the sources in this flow network. The green nodes are sinks. They are the utilities in the All Country World Index (MSCI ACWI) and are scaled by the MW of power reaching them directly or via the network of subsidiaries (blue nodes).

The right hand side of the figure reveals the piping in the network, where the nodes are removed and only the weighted and directed ownership links are shown.

This is an example of climate finance, a topic slowly appearing on the radars of institutions. See, for instance, Mark Carney's speech, as Governor of the Bank of England.

Data sources: GlobalData and Orbis. The work is done for the SEI Metrics Project.

decoding complexity

complex systems update
I was recently asked to write something about the study The Network of Global Corporate Control in The Montreal Review. This is what I came up with...

***

DECODING COMPLEXITY

THE ORGANIZING PRINCIPLES BEHIND OUR ECONOMY

***

By James Glattfelder

***

The Montreal Review, April 2012

***

"We spend billions of dollars trying to understand the origins of the universe, while we still don't understand the conditions for a stable society, a functioning economy, or peace."

Dirk Helbing, Professor of Sociology at ETH in Zurich (source)

***

It sounds paradoxical, but today it appears that we understand more about the universe than our society. We have created systems, that have outgrown our capacity to genuinely understand and control them. Just think about the Internet or the financial markets.

On the one hand, we are drowning in data. In 2007 Wired magazine heralded the arrival of the "Petabyte Age", plagued by the data deluge. Endless streams of data are continually flowing along global information super-highways, being stored in countless server farms around the world. On the other hand, while data can be mined and its potential harnessed, the biggest obstacle in understanding our own constructed socio-economic world has been nearly invisible. It came in the guise of a weltanschauung and is being currently conquered by a paradigm shift in understanding.

Our traditional ways of thinking and problem solving have been strongly shaped by the success of the reductionist approach taken in science. The fabric of the universe is broken down into its constituents, who's interactions are described by four fundamental forces. Information is boiled down to an irreducible physical entity: the bit. This thinking has been at the heart of the Scientific Revolution and the dawning of the Information Age, unlocking spectacular technological prowess. Put in the simplest terms, the focus has been on "things". Tangible, tractable and malleable.

Not so long ago, it was realized that there is an other, a more subtle dimension to our reality: things are not isolated! Ideas like interconnection, co-dependence and collective dynamics entered the stage. Indeed, this is the aspect of our world that has changed most in the past decades. While the things themselves still look pretty much the same, they have become highly networked and interdependent. The tools to grapple with this new era come from the field loosely known as complexity science.

In 1972 the Nobel laureate P. W. Anderson wrote an influential article in Science, planting the seeds for this new science, emerging from systems theory and cybernetics:

"At each stage [of complexity] entirely new laws, concepts, and generalizations are necessary [. . .]. Psychology is not applied biology, nor is biology applied chemistry."

Understanding a systems components' individual properties does not bring insights into how the system will behave as a whole. Indeed, the very concept of emergence fundamentally challenges our knowledge of complex systems: self-organization allows for novel properties to emerge, features not previously observed in the system or its components. The whole is literally more than the sum of its parts.

Although the paradigm shift, moving away from reducing to components towards analyzing interactions, seems to entail hopelessly complicated systems, it is a notable fact that also complex systems are characterized by laws and regularities. Most prominent are scaling-law distributions, also called power laws. Like a normal distribution, it quantifies what the frequency of an observed trait in a population is. Scaling-law distributions have been observed in an extraordinary wide range of complex systems: from physics, biology, earth and planetary sciences, computer science, demography and finance to the social sciences. In a nutshell, a scaling law says: most components are unimportant, very few are very important.

Regarding economics, already in 1897 V. Pareto observed that household income is distributed according to a scaling law. Called the Pareto principle, or the 80-20 rule, this still holds today. The aphorism introduced at the end of the last paragraph has a whole new quality, now that it describes the realm of human affairs: nearly all have very little and very few have very much. Suddenly a general organizing principle of reality has an unjust and undemocratic feel to it.

The Network of Global Corporate Control 

A recent example uncovering the patterns in an economic system, raising the issues of concentrated power, systemic risk and market competition, is the study: The Network of Global Corporate Control [1].

Complex systems find a natural formal representation as networks, where the links describe the interaction structures. The study of complex networks has been extremely fruitful in the past decade and has uncovered many features of the physical, biological and social worlds. This is quite remarkable, as complex systems are usually very hard to understand employing mathematical equations, i.e., applying the standard scientific approach.

In the study, ownership data of 30 million economic agents (i.e., natural persons, foundations, government agencies, listed and unlisted companies, etc.) from early 2007, located in 194 countries, was analyzed. By focusing on the 43,000 transnational corporations (TNCs) in the sample, a network was constructed with 600,000 nodes and 1,000,000 links (all numbers are approximations).

Already the topological structure of this ownership network reveals a surprising organizational structure. Whereas 64% of the TNCs are distributed among many small isolated clusters of a few nodes, the remaining 36% are located in a single giant connected network of 460,000 nodes. Interestingly, this minority of TNCs accounts for 94% of the total operating revenue of all TNCs. Moreover, the 460,000-node network has a tiny but distinct core of 1,300 nodes, seen in Figure 1.

Figure 1 (PLoS ONE)

By introducing a methodology that estimates the potential degree of control resulting from a network of ownership relations, it is possible to identify the most important nodes. It turns out that 730 top shareholders are able to control 80% of the operating revenue of all TNCs. Furthermore, combining the knowledge of the topology with the ranking of shareholders, it is revealed that the 1,300 nodes in the core are comprised of the most powerful nodes in the network: the top economic agents are interconnected and do not carry out their business in isolation (a small excerpt is given in Figure 2). Finally, the core is able to gain 39% of the potential control.

Although these numbers show an unprecedented high level of concentration, simulations suggest that this could all be the result of the interaction rules in the system. Contrary to common intuition, it is not necessary to have a puppet-master behind the scenes, orchestrating such a large concentration of power for self-enrichment. Inequality can be an emergent property. It is also an interesting side note, that the complex systems paradigm, with its empirical and data-driven foundation, its interaction-based methodology, is only very slowly being adopted in economics and finance.

Figure 2 (PLoS ONE)

Where Do we Go from Here?

These observations could possibly have very important implications for the global economy. The observed organizational patterns could endanger market competition and financial stability. "Too connected to fail" being the next predicament our economy faces. However, in order to validate these concerns an additional interdisciplinary effort is required.

This is the current state of things in dealing with socio-economic systems. We can improve our understand of their organizing principles, highlight potential weaknesses and looming threats. But to give concrete advice and formulate effective policies is a whole different story. Ambitious, long-term and highly-funded programs like futurICT (an EU FET Flagship Initiative), the UN's GlobalPulse or the US' Big Data R&D Initiative are currently trying to close this knowledge gap. The efforts aim at crafting new technologies and innovations building on a complex systems point of view, but are still at the level of data collection or project formulation.

Ideas relating to economics, finance, politics and society are very often tainted by individual ideologies. In contrast, decoding the complexity of our world by considering its interconnected and interactive nature, not only brings novel understanding, but perhaps also allows for a neutral perspective to emerge in the not too distant future. Reality is so complex, we need to move away from dogma.

***

James B. Glattfelder holds a M.Sc. in theoretical physics and a Ph.D. in the study of complex systems, both from the Swiss Federal Institute of Technology. He co-authored the study "The Network of Global Corporate Control" which was recently covered in dozens of news media world-wide and sparked controversial discussions. He is a senior researcher at Olsen Ltd, a quantitative FX investment manager in Zurich, focusing on market-stabilizing algorithms. His interests include the philosophy of science next to societal issues. You can follow him here http://twitter.com/jnode and here http://gplus.to/jnode, and read his blog here http://j-node.blogspot.com/.

***

[1] Stefania Vitali, James B. Glattfelder and Stefano Battiston; PLoS ONE 2011, 6(10): e25995; 2011
(Watch a TEDx talk about it.)

***

quotes of the day...

mood: bewilderment
sometimes, psychology (wishful thinking, denial, cognitive bias, blind spots, ideology, ...) is stronger than intelligence.

alan greenspan's comments on the financial/economic crisis:

I found a flaw in the model that I perceived is the critical functioning structure that defines how the world works, so to speak.

That's precisely the reason I was shocked because I was going for forty years or more with very considerable evidence that it was working exceptionally well.

those of us who have looked to the self-interest of lending institutions to protect shareholders equity, myself especially, are in a state of shocked disbelief.

source oversight.house.gov.