- 金币:
-
- 奖励:
-
- 热心:
-
- 注册时间:
- 2002-6-22
|
|

楼主 |
发表于 2002-11-25 21:53
|
显示全部楼层
好文重贴/第1-13次更新/详情见说明^^^^^^
Trust me, I'm an expert
6 December 1997
Would you allow a machine to play the stock market with your life savings? Well, the people in the know are doing just that, says Clive Davidson By Clive Davidson
IT'S THURSDAY 23 OCTOBER and it's hell. The Hong Kong stock exchange has just taken a nose dive and brokers everywhere watch in a mixture of fear and fascination as the rest of the world's markets follow suit. Should they sell now and cut their losses? Should they buy while prices are crashing down in the hope that the markets will pick up? Or should they hold their breath and wait for the storm to play itself out? Only good instincts will save them from doom.
To varying degrees, "the hunch" is what life as a dealer or analyst is all about. Even in less extreme conditions, they need to ask themselves a thousand questions a day. Is the latest interest rate hike good or bad? Is the market overvalued? How will a company's share price react to a financial scandal? Hardly surprising then that this volatile, nervy world would be deeply resistant to any attempt to turn those well-honed hunches into smart software, capable of making decisions to buy or sell. And yet, slowly, reluctantly, cautiously, the financial world is starting to put its faith-and loads of money-into artificial intelligence.
To be fair, we've been here before. Finance houses got excited about AI in the late 1980s. But on that occasion, early success was swamped by failure. Today's excitement surrounds groups that have persevered with AI ever since, not sticking with one technique but combining different methods. Some of the world's wealthiest and most conservative institutions are now handing their money to the machines these groups created. In October, the Boston-based State Street Global Advisors, the third largest investment management company in the US, took over Advanced Investment technology (AIT) of Florida, a pioneering designer of electronic analysts. So mainstream finance houses are moving in on AI.
In London, Pareto Partners manages about $20.5 billion for government and corporate pension funds. When it was set up in 1991, its director of research, Ron Liesching looked for a partner with whom to develop technology to help make complex investment decisions. He already knew how hard it would be to build this technology. "There's a lot of noise in the data," he says. "And you've got to get the job done reliably. If you're wrong, you're gone." Realising that financial markets are like war zones, Liesching cast his eye towards the military's research labs. At Hughes Electronics, a California-based contractor to the US Department of Defense, Liesching found what he was after: an expert system for extracting and automating the thought processes of battlefield officers.
An expert system is a program that encapsulates the specialist knowledge of an expert, which others can use to take the expert's place. The hardest part of building such a program is converting that knowledge into software. People are often not aware of the reasoning they use to come to a decision, or find it hard to quantify their judgments. How, for example, does a tank commander make the trade-off between achieving an important military objective and the heavy troop losses this action could lead to? Even if the reasoning can be worked out, there's the problem of translating terms such as "trade-off", "important" and "heavy" into computer code. To extract and define these sorts of terms and thought processes, developers of expert systems have evolved a set of techniques they call knowledge engineering.
Most existing expert systems tend to operate in areas where problems are solvable by straightforward reasoning, such as backward or forward chaining. Backward chaining is where the expert starts with a hypothesis and tries to work out whether it is true. For example, a doctor who thinks a child has measles might check the patient's symptoms to decide whether this hypothesis is true. In forward chaining, the expert starts with the symptoms and works forwards to conclude that the child has measles. Unfortunately, financial trading is often much more complicated, involving many variables and different ways of reasoning, says Liesching. Conventional expert systems proved too inflexible for analysing global bond markets.
Evolving intelligence
At Hughes, researcher Charles Dolan used a mixture of old and new AI ideas to develop the system that caught Liesching's eye. Expert systems take a "top-down" approach, in which scientists attempt to analyse an aspect of intelligence and then write a program to simulate it. But in recent years, scientists have experimented with "bottom-up" approaches: they build a model of an organic structure or process, which they then set running to "learn" or "evolve" intelligence.
Neural networks are the best-known example of this way of doing things. Scientists "train" a neural network by presenting it with examples of a problem-such as identifying a car in a digital image of a street-and adjusting the connections between the neurons until the network produces the correct output-say, drawing an outline round the car-for every example (see Diagram). This "connectionist" approach allows scientists to simulate an intelligent process even when they don't understand it in a way that can be captured in equations.
Diagram: Every node, or neuron, receives a weighted input from nodes in the layer below. If the sum of the inputs is big enough, the node fires a signal up to the next layer. To "teach" the device, training data is fed in and the weightings tweaked until the network gives the correct output. It is then tested on more known data. Expertise resides in the pattern of weightings between the nodes.
Dolan's innovation has been to use similar thinking to generate sophisticated expert systems. Rather than attempting to reduce a person's expertise to a single orderly list of facts and rules, Dolan creates a complex network of different thought processes that interact to reach a decision, in much the same way as neurons in a network do. He has developed a suite of programs, called Modular Knowledge Acquisition Toolkit (M-KAT), that mimics different ways of thinking to help extract and model an expert's knowledge.
With his toolkit, Dolan modelled the thinking of Christine Downton, Pareto's bond market expert. Downton is a star analyst with 20 years' experience as an academic, fund manager and banker. Over a period of 18 months starting in 1993, she flew regularly to Los Angeles for brain-dumping sessions with Dolan.
The most difficult part of the task was capturing how Downton homed in on key information hidden in a mass of economic data-an ability called "feature extraction". At a glance, Downton can tell if an economic measure is "high" or "low", or if a price has moved "a lot" or "a little" and so on. The system had to "look at a particular number and come up with exactly the same assessment as I would", says Downton. To make it do this, Dolan brought fuzzy logic into play.
Fuzzy logic allows computers to cope with these imprecise sorts of assessment. The trick is to ignore the actual value of, say, a financial variable. Instead, fuzzy logic programs look at where the value stands within its range of potential values. So, for example, if the current inflation rate falls within the lowest 20 per cent of its potential range it would be considered "low", while if it is within the top 20 per cent it would be seen as "high". The rules of inference of fuzzy logic work with these "fuzzy" values to reach conclusions where there are no precise answers.
Dolan boiled down Downton's expertise to some 2000 rules. The system, called the Global Bond Allocation Strategy, runs on an Apple Macintosh. Every month it pulls in around 800 items of economic information on 14 bond markets, taking them directly off electronic data feeds. This information includes countries' public sector borrowing requirements (PSBR), unemployment figures, inflation rates, money supply figures and so on.
Undervalued
Dolan's system automates the process that Downton would use to decide which bonds are overvalued and which are undervalued. The computer can look at a bond price and say to itself the equivalent of: "Mmmm, this looks high given the country's interest rate, I wonder what direction other economic indicators, such as PSBR, are pointing?" Towards the end of the process, the system compares its new analysis of every bond with stores of typical cases. If the situation of any bond or group of bonds resembles a past situation, it will consider the way the market developed on that occasion. Finally it recommends a series of bond trades.
Financial regulations mean that Downton must keep an eye on the system, but she never interferes with its decisions. Nevertheless, for the final step, the machine has to hand over to a person. Physically trading the bonds is still the exclusive preserve of humans, so its recommendations are passed to a trader to strike the deals.
Humans also do the physical trading at AIT in Florida, which deals on American stock markets on behalf of pension funds. But, once again, computers decide which trades to make. Every week AIT's machines sift through 24 million pieces of information and evaluate 3000 stocks, searching for clues as to which will rise in price and which will fall. As well as stock prices, they take account of details such the earnings estimates of quoted companies, their cash flows, and current book values-their assets minus liabilities.
The enormous volume of data was not the only barrier that needed to be overcome in designing the system, says Dean Barr, president of AIT. Factors such as earnings, cash flow and book value interact with one another and affect the stock price in "nonlinear" ways. In other words, a combination of tiny changes in some of the indicators can trigger a massive shift in the stock price. Conventional mathematics cannot deal with systems that exhibit this kind of behaviour-which is where the new AI comes in.
Just like financial variables, the neurons in a neural network interact in nonlinear ways. So when AIT looked for ways to simulate the relationships between the principal financial variables and stock price, neural networks were a natural choice. Once the network has been trained to associate past financial data with ensuing stock prices, it should be able to calculate the likely stock price from any new values for the variables.
But creating a neural network system is not just a matter of shovelling in any old data and waiting for a forecast to pop out the other end. Selecting the right network architecture and variables to feed in, and choosing which historical data to use to train and test it, all influence the success of the analysis, says Barr. The chosen combination is a closely guarded company secret.
The kind of pitfalls that exist is exemplified by the military researchers who tried to teach a neural network to identify tanks in a landscape. They trained the network on photographs of scenes in which tanks were present or absent. When they tested the network on a new set of images it performed brilliantly. Only then did the researchers realise that all the images with tanks had been taken on a bright day, while scenes without tanks had been photographed on a dull day. The network, it turned out, had learnt to differentiate between dull and bright skies. It didn't look for tanks at all.
To avoid this kind of blunder, AIT carves up its data on stocks in several different ways and runs the learning and testing routines several times. To give added assurance, AIT also makes alternative forecasts with genetic algorithms-programs that can "evolve" a solution to a problem, starting from a set of random solutions. A genetic algorithm treats a problem as an "environment" and solutions as "life forms" struggling to flourish. The program forces the solutions to evolve over many generations until it identifies the "fittest" life form for the environment-which is the optimal solution.
Fitness test
Suppose the problem is to find which set of economic variables best predicts future movement of a company's stock. The algorithm first generates a set of solutions, each of which includes some or all of the variables, randomly weighted and added or multiplied together in different ways. Next, it subjects each solution, encoded as a string of 1s and 0s, to a "fitness test" to measure how well it tracks the stock price movements.
Unsuccessful solutions are killed off, while more successful ones survive into the next generation. The algorithm enhances the evolutionary process by allowing some surviving solutions to "mate", by swapping sections of code with other successful solutions. It also "mutates" them by changing a few 1s into 0s and vice versa. The new set of solutions then undergoes the fitness test again, and the process is repeated over and over until an optimal solution evolves.
For every stock that AIT trades, it has built an electronic analyst-each made up of several neural networks and genetic algorithms. These elements work independently, forecasting future stock price movements by analysing past movements or by checking sets of information about the company itself. Near the end of the process, the electronic analyst holds a "committee meeting" at which it combines the various elements' forecasts to produce a recommendation to buy, hold or sell.
The systems at Pareto and AIT are the state of the art in applied artificial intelligence. The question that really matters, though, is how well they perform. Pareto's Global Bond Allocation Strategy began operating in September 1994 and has been coming in at around 4.1 per cent above the bond market benchmark-a reference point based on a portfolio of key bonds. These rewards are modest, but then Pareto has tuned its system to a low-risk strategy because of the conservative nature of its clients. The returns have been good enough for Pareto to attract an increasing flow of funds from clients such as the respected Mellon Bank, based in Pittsburgh, Pennsylvania. In Florida, AIT's longest-running portfolio of stocks has shown an average annual return over three years of 4.5 per cent above the Standard & Poor 400 stock index benchmark-a selection of 400 leading US stocks.
But are the machines doing any better than the humans they are replacing? In terms of performance, the Global Bond Allocation Strategy is in the top quarter of investment management funds in the same market. Downton thinks her electronic clone has some significant advantages, particularly because computers don't suffer from stress or emotional disturbances. "Emotions distort people's rational judgments," she says. "There's a fear factor in managing money. People tend to make mistakes when they're losing money. They also make mistakes when they've made money, because they get big-headed."
Liesching sees similar advantages. Expert systems do not suffer from "cognitive biases", he says. Humans can become fixated on one variable, or get hung up on the most recent piece of information they receive. "Investors frequently focus on one or two factors at a time, rather than assessing the whole environment," he says. This can mean they miss important developments elsewhere.
There is also a difference in brute processing power. "Every weekend our electronic analysts are evaluating 3000 stocks against new information using adaptive techniques," says Barr. "They do it with so much speed and efficiency I don't think people can compete."
Act of faith
But if computers are so fast and efficient, why isn't everybody using them? The two big reasons are time and money. Developing AI for the financial sector has taken determination and long-term commitment, says Barr, and in the financial sector the latter is in particularly short supply. "The typical Wall Street attitude is if you don't get quick results you drop it," Barr says. AIT set out to do things differently. "Our company was created with the concept that we would see this thing through to the finish line," Barr proclaims. And it's an expensive business. Liesching reckons it costs at least £1 million to test a new expert system or neural network.
But many analysts and traders are still suspicious about AI, believing that its success will be short-lived. They say the reasoning underlying today's AI systems is based on data from a particular set of market conditions. As the market moves, those conditions will inevitably change, leaving the machines high and dry.
Barr rejects such pessimism. Human analysts keep a close eye on their electronic counterparts and constantly tweak them, so they learn all the time. "We are not defying the laws of physics," says Barr, but evolving techniques that analysts have applied for decades. Downton regularly analyses the bond markets to see if they have changed in some fundamental way that would undermine Pareto's expert system. So far they haven't.
Today, an increasing number of big financial institutions, including the Banque Nationale de Paris and the World Bank, are experimenting with AI. State Street Global Advisors has set up its own AI laboratory with Barr at the helm. Other firms using AI include the New York-based bank D. E. Shaw and the Prediction Company of Santa Fe, New Mexico, which is working for the investment bank SBC Warburg Dillon Read. But these are reluctant to reveal what they're up to.
If interest in AI continues to grow, perhaps analysts have good reason to worry. AIT's machines do the jobs of hundreds of humans. According to Liesching: "People in finance are generally overpaid, under-qualified and there are too many of them. Whoever can replace these people with machines will win-even if the machines are only half as good-because they can work 24 hours a day." The systems at Pareto and AIT are in the vanguard of a process of automation that will rock the financial industry to its foundations, says Liesching. Anyone tempted to reject this as just another wild claim of AI enthusiasts should take note: the message is coming not from computer scientists in ivory towers but from people who are prepared to put big money where their machines are.
|
|
|