Friday, February 11, 2011
Wednesday, January 19, 2011
Hypothetically interesting
I found out about Elizabeth Pisani’s Prospect article through its publication in the Australian Financial Review on 14 January 2011 as Hypothetical Crisis but was originally published on 17 November 2010 in Prospect. However, it gave me some food for thought regarding many areas where data and is used to make decisions and build models.
The article’s starting premise is that the internet age has changed science by making its “… tidy world of hypothesis, experimenting and knowledge generation…” obsolete and “… about to end”.
This ending of the current paradigm is driven home to the author by “Generation Y geeks” telling her that it’s all about scraping, data mining, terabytes and even petabytes of data. The article is worth reading as it asks many probing questions for anyone who works in any forecasting/model building area.
Let me first be upfront with my bias that theory(hypothesis) is as relevant as ever by retelling a story that I heard when I was a physics undergrad. The story was told by one of my professors, who was an experimental physicist but of a rare breadth and depth to have full appreciation of how the whole physics(theory and experiment) progresses together. At any rate, the story went that … in the sixties Australia had one of the world’s most powerful telescope arrays but as a scientific community it had not invested enough in theoretical physics so in effect they did not know where to “point” it.
The moral of the story is that no matter how much data you can amass, it has to be the right data and that data and its analysis are strictly theory led.
This is not to say that those that are algorithmic champions don’t have a point – they do – but I believe that they only have a point in a limited sense. For example when taxonomy is required or when a model/hypothesis builder is in pre-discovery mode.
It is easy to imagine that algorithmic analysis and high CPU power can lead to fast categorisation of data – say like cluster analysis.
The discovery mode is also important because model building is a trial and error business and the only way to get the intuition to be strong enough to see hidden relationships is by “getting ones hands dirty”.
My professional interest is in financial modelling and the way that organisations build and maintain models. In this field the purely quantitative approach can lead to disaster because often relationships break down at other times they are circumstantial. Moreover the communication aspects of a purely algorithmic approach can be tortured and lead to devastating outcomes of inappropriate usage by users like bankers, traders etc. This is because it is by creating theoretical explanations that we can tell a story that people relate to.
However in all fields that really seek to explain and understand the structure of the world the algorithmic approach is a “first approximation”, a heuristic and handmaiden to intuition but theory leads to deepening, which can then use the data to test it.
On a final note and paradoxically the algorithmic/data mining approach is almost unthinkable as a tool to discover Quantum Mechanics, which is the necessary condition of the microchip hence computer.
The article’s starting premise is that the internet age has changed science by making its “… tidy world of hypothesis, experimenting and knowledge generation…” obsolete and “… about to end”.
This ending of the current paradigm is driven home to the author by “Generation Y geeks” telling her that it’s all about scraping, data mining, terabytes and even petabytes of data. The article is worth reading as it asks many probing questions for anyone who works in any forecasting/model building area.
Let me first be upfront with my bias that theory(hypothesis) is as relevant as ever by retelling a story that I heard when I was a physics undergrad. The story was told by one of my professors, who was an experimental physicist but of a rare breadth and depth to have full appreciation of how the whole physics(theory and experiment) progresses together. At any rate, the story went that … in the sixties Australia had one of the world’s most powerful telescope arrays but as a scientific community it had not invested enough in theoretical physics so in effect they did not know where to “point” it.
The moral of the story is that no matter how much data you can amass, it has to be the right data and that data and its analysis are strictly theory led.
This is not to say that those that are algorithmic champions don’t have a point – they do – but I believe that they only have a point in a limited sense. For example when taxonomy is required or when a model/hypothesis builder is in pre-discovery mode.
It is easy to imagine that algorithmic analysis and high CPU power can lead to fast categorisation of data – say like cluster analysis.
The discovery mode is also important because model building is a trial and error business and the only way to get the intuition to be strong enough to see hidden relationships is by “getting ones hands dirty”.
My professional interest is in financial modelling and the way that organisations build and maintain models. In this field the purely quantitative approach can lead to disaster because often relationships break down at other times they are circumstantial. Moreover the communication aspects of a purely algorithmic approach can be tortured and lead to devastating outcomes of inappropriate usage by users like bankers, traders etc. This is because it is by creating theoretical explanations that we can tell a story that people relate to.
However in all fields that really seek to explain and understand the structure of the world the algorithmic approach is a “first approximation”, a heuristic and handmaiden to intuition but theory leads to deepening, which can then use the data to test it.
On a final note and paradoxically the algorithmic/data mining approach is almost unthinkable as a tool to discover Quantum Mechanics, which is the necessary condition of the microchip hence computer.
Tuesday, November 16, 2010
Market Belief System
Finance needs its own Dirac or Where to for Economics after the Global Financial Crisis...
There's been a lot of discussion on what went wrong in financial markets that lead to the Global Financial Crisis (GFC) of 2007.
Some of the views around have blamed the Quants, others fraud, whilst others point to greed and naive belief in markets. Former US president George W Bush captured it with a great one liner "Wall Street got drunk".
The common thread of most reviews and opinions on the GFC is that the complexity of the instruments was the major problem.
Complexity is not unique to Wall Street or that Wall Street is much more complex than other areas of technological and professional endeavour.
We only have to think about the Space Program, Medical Science, Planning Wars etc.
Complexity in and of itself is not the problem but something we must live with because it is part and parcel of the human condition.
Whilst complexity alone may not be responsible, it is fascinating how weak theory finds its way in financial practice that would not in other fields.
It's all the more fascinating because if you walk into a trading room and talk to seasoned traders, you very quickly conclude that they are at best condescending of theory, especially the so called Efficient Market Hypothesis (EMH) - yet they use models!!
A similar trip to Risk Department is disturbing because you will find people espousing market efficiency, dynamic hedging etc.
In fact modern financial risk management infrastructure is built around EMH and its corollaries, due to its adoption into regulatory frameworks and business schools.
We must seriously evaluate any theory that leads to this kind of confused practice. If a theory had a large body of empirical evidence behind it we may tread a little more carefully, but EMH is full of caveats on why it can't be observed ... due to market imperfections.
EMH does lead to mathematical formulations but Economics is not Physics and it should not be so enamored by the success of Physics and assume that if it adopts its major tool - Mathematics - it too will be just as successful in predicting the world.
Economics needs its own style that utilises math where appropriate but should not fall into a reductionist trap, which will only harm it.
Economics needs its own style that utilises math where appropriate but should not fall into a reductionist trap, which will only harm it.
Moreover and as far as I know a case has not been made why math suits economics so well.
Even though physics is suited to math, physicists tried to understand the effectiveness of mathematics to explaining nature (see Eugene Wigner's famous article).
If a lesson must be sought in the success of physics, the early 20th century physics revolution is a good place to start.
It's a good place, because it started by two seemingly small things, namely Blackbody Radiation and Maxwell's Electrodynamics not quite fitting in with the known physics.
This is not to say that physics did not have work-arounds to explain away the anomalies, but revolutionary steps were taken that overthrew the accepted orthodoxy.
The old order of Classical Mechanics did not completely disappear but came back when Dirac astonishingly realised that much of it could be reinterpreted.
Physics had to abandon long held views of the universe and learned a new vocabulary that pretty much guaranteed that it could no longer have a "picture" of nature.
It's clear that economics needs to undergo a revolution, since a central principle (ie EMH), so embedded in policy and theory, has failed so comprehensively in the GFC.
Economics is trying other ideas from psychology, behavioural science and many other areas, but as since these have been around for a while and not really made the kind of impact that is needed, given the importance of the subject in everyday life, the chances are that the revolution will probably come out of nowhere like in physics ... and perhaps find its own Dirac too.
PS - Economics is much harder than physics, because anything useful gets political Maybe this aspect of economics may hold back progress and perhaps the attempt at mathematising the subject was made to remove the subjective element. They don't call it the "dismal science" for nothing.
Subscribe to:
Posts (Atom)