Showing posts with label deep uncertainty. Show all posts
Showing posts with label deep uncertainty. Show all posts

Friday, January 10, 2020

9/1/20: Herding and Anchoring in Cryptocurrency Markets


Our new paper, with Daniel O'Loughlin, titled "Herding and Anchoring in Cryptocurrency Markets: Investor Reaction to Fear and Uncertainty" has been accepted to the Journal of Behavioral and Experimental Finance, forthcoming February 2020.

The working paper version is available here: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3517006.

Abstract:
Cryptocurrencies have emerged as an innovative alternative investment asset class, traded in data-rich markets by globally distributed investors. Although significant attention has been devoted to their pricing properties, to-date, academic literature on behavioral drivers remains less developed. We explore the question of how price dynamics of cryptocurrencies are influenced by the interaction between behavioral factors behind investor decisions and publicly accessible data flows. We use sentiment analysis to model the effects of public sentiment toward investment markets in general, and cryptocurrencies in particular on crypto-assets’ valuations. Our results show that investor sentiment can predict the price direction of cryptocurrencies, indicating direct impact of herding and anchoring biases. We also discuss a new direction for analyzing behavioral drivers of the crypto assets based on the use of natural language AI to extract better quality data on investor sentiment.

Friday, February 24, 2017

23/2/17: Welcome to the VUCA World


Much has been said recently about the collapse of ‘risk gauges’ in the financial markets, especially on foot of the historically low readings for the markets’ ‘fear index’, VIX. In terms of medium-term averages, current VIX readings are closely matching the readings for the period of ‘peak’ ‘Great Moderation’ of 1Q 2005 - 4Q 2006, while on-trend, VIX is currently running below 2005-2006 troughs. In other words, risk has effectively disappeared from the investors’ (or rather traders and active managers) radars (see chart below).

At the same time, traditional perceptions of risk in the financial markets have been replaced by a sky-rocketing uncertainty surrounding the real economy, and especially, economic policies. The Economic Policy Uncertainty Indices have been hitting all-time highs globally (see chart below), and across a range of key economies (see this for my recent analysis for Europe: http://trueeconomics.blogspot.com/2017/01/15117-2016-was-year-of-records-breaking.html, this for Russia and the U.S.: http://trueeconomics.blogspot.com/2017/01/17117-russian-economic-policy.html). In current data, Economic Policy Uncertainty Index (EPUI) has been showing extreme volatility coupled with extreme valuations. Index values are rising above historical norms both in terms of medium-term averages and in terms of longer term trends.


 Another interesting feature is the direct relationship between the EPUI and VIX indices. Based on rolling correlations analysis (see chart below), the traditionally positive correlation between the two indices has broken down around the start of 2Q 2016 and since then all three measures of correlation - the 6-months, the 12-months and the 24-months rolling correlations - have trended to the downside, turning negative with the start of 2H 2016. Since November 2016, we have a four months period when all three correlations are in the negative territory, the first time this happened since June 2007 and only the second time this happened in history of both series (since January 1997). Worse, the previous episode of all three correlations being negative lasted only two months (June and July 2007), while the current episode is already 4 months long.


Final point worth making is that while volatility of VIX has collapsed both on trend and in level terms since the start of H1 2016 (see chart below), volatility in EPUI has shot up to historical highs.


Taken together, the three empirical observations identified above suggest that the current markets and economies are no longer consistent with increased traditional risk environment (environment of measurable and manageable risks), but instead represent VUCA (volatile, uncertain, complex and ambiguous) environment. The VUCA environment, by its nature, is characterised by low predictability of risks, with uncertainty and ambiguity driving down efficacy of traditional models for risk assessments and making less valid traditional tools for risk management. Things are getting increasingly more complex and uncertain, unpredictable and unmanageable.

Sunday, February 13, 2011

13/02/2011: What a Jeopardy champ can do in the world of finance

Here is my article along with Shanker Ramamurthy that was published last Thursday in the American Banker, discussing IBM's Watson super computer system's potential applications in the financial services industry - helping to advance industry thinking on how in the era of "big data" only advanced non-linear analytics can make sense of structured and unstructured data flows to transform it into valuable insights.

VIEWPOINT: New Computer, New Modeling Possibilities
By Shanker Ramamurthy and Constantin Gurdgiev
February 10 , 2011 - p8

Next Monday a new IBM computer system called Watson will battle two quiz-show champions in a game of Jeopardy! There is more at stake here than winning a game. The potential applications of this technology to transform the operations of industries such as health care, government and finance are enormous.

In the financial services industry, integrated risk management is an everyday struggle. Financial practitioners and supervisory and regulatory authorities must make split-second decisions using information coming from all sides: the Internet to corporate and call center channels.

The challenge is to efficiently process diverse data streams and pick out relevant data insights to apply to strategic business and regulatory decisions.

In the banking industry today, data "fuzziness" abounds. Uncertainty exists about the quality of data, assumptions and models that are being used to make judgments. This, of course, clouds the true picture of risk and biases our decision-making, often in econometrically undetectable ways.
Most banks today run risk models on a discrete and disaggregated basis while relying on often subjective assumptions. High-performance computing advances, represented by Watson's capabilities, can rectify this - by providing visibility into concentrations of risks and risk-related activities, as they happen. Simultaneously, it deploys nonlinear analytics in selecting both the statistically and operationally important scenarios.

The beauty of a nonlinear computer that "learns" is that it can analyze a complex set of implied possible scenarios and give answers to the broadest set of questions. This potentially can lead to the emergence of analytical systems that not only report on probabilistically likely events but also identify latent "Black Swan" events and even sense deeper levels of uncertainty.

For example, a legislative decision altering a specific set of financial strategies can have no impact on traditional linear models because the outcomes can be weighted by an extremely low assigned or assumed probability. But in a nonlinear world, such an outcome can still be testable as part of the selection list for reporting. More importantly, it can be made recognizable by the analytic system and, therefore, objectively reportable.

A system like Watson has the potential to get answers to incredibly difficult questions about strategic decisions, risks and market changes that can otherwise be elusive.

For example, it has the ability to create an interactive risk-pricing system using a menu of models that evolve as the system learns, detecting structural breaks in data before analysts can spot them and build them into existing programs.

Of even more significance, Watson will be able to deliver scenario analysis based not just on either event probability or expected loss/gain but also on more complex company objectives.

This can involve analyzing corporate strategy inputs, including non-quantifiable questions, alongside fully quantifiable inputs. Imagine asking a computer "How do I increase my loan book profit margin by 10%?" or "What actions can I take to strengthen my capital reserves, with minimum impact to my asset base?"

At a much deeper level, the nonlinear learning capabilities that Watson pioneers can lead to the creation of systems that are able not only to handle traditional risks and their interactions but also to evolve into systems capable of transforming deep uncertainty into explicit models. Though still some years away, this could mean an artificial intelligence able to sense Donald Rumsfeld's famous "unknown unknowns," converting them into specific models suitable for risk analysis and getting meaningful, actionable responses.

The real-time, decision-making capability that is so sought after in the financial industry will be a crucial, competitive differentiator.

As risk intensifies within interconnected global markets, the complexity and exploding volumes of data will only rise.

Shanker Ramamurthy is the general manager of banking and financial markets at IBM Corp. Dr Constantin Gurdgiev is the head of macroeconomics in the Center for Economic Analysis at the IBM Institute for Business Value.