Technical Analysis does have its critics – those economists who say it is nothing more than a pseudoscience, one that has no basis in fact. Investors such as Warren Buffett and Peter Lynch say that there is precious little evidence that Technical Analysis works. However, various academic studies have shown that technical analysis, particularly when carried out by neural networks, can produce statistically significant returns, and many investors have made fortunes through the application of its principles. It is therefore unfair to dismiss it as mere nonsense, and one ignores it at one’s peril!

Computer software lends itself readily to the processing of massive amounts of data, and they are ideal tools to use in Technical Analysis. There are two broad approaches to the automatic prediction of shares: those that use rule-based prediction (where the computer program is fed certain predetermined rules about how shares generally behave and when to buy or sell) and those that use neural networks (software based on networks of brain cells). Neural networks are trained by example on sets of data and which hone their prediction abilities as they accumulate experience.

One of the tenets of Technical Analysis is that prices follow trends, either upwards, downwards or sideways (when the price is generally holding steady – a “flat” price). If investors spot an upward trend in a share, they may well try to jump on the band-wagon and buy that share, hoping to benefit from its rise, and thereby driving its price up further. Similarly, a downward trend may cause investors to dump shares on the market, causing a further fall in the price. This can cause the price to “zig-zag” – rise and fall several times in line with investor confidence.

Technical analysis covers two areas of the stock market, its sentiment (sometimes termed its “psych”) and the analysis of supply and demand. The sentiment of the market is the general feeling of investors. This is rather intangible, but does show itself in overall share movements. For instance, if investors are feeling generally optimistic (as in a bull market), share prices will tend to rise. The supply and demand aspect of the stock market is a measure of how much money there is available to invest in shares: If an investor has little spare money, for example, this restricts his or her ability to invest in shares and drive the market higher.

Any stock market produces vast amounts of data on a daily basis, far too much for anyone to cope with in its raw form. You only have to look at the share price pages in the Financial Times to get some idea of the quantities of figures that make up just one day’s trading. To make any sense of this deluge, we must apply various statistical measures that turn the raw data into meaningful information. There are several measures in common use, and different technical analysts tend to prefer different measures. These measures all have one thing in common – they reduce the amount of noise present on the data and help to reveal any underlying pattern.

The Purpose of Technical Analysis

Inevitably, the ultimate aim of Technical Analysis is to make money. The secret of successful share trading, boiled down to one sentence, is to buy when the share price is low and to sell when it is high. As the share prices rise and fall, there will be times when one makes the correct judgement and makes a profit, and times when one gets it wrong and makes a loss. With successful technical analysis, the accumulated profits will outweigh the total losses.

What is Technical Analysis?

Technical analysis is the science (some might say art) of predicting the prices of share commodities based on their current price and past performance. Share prices wander up and down, changing many times every day. If you plotted the price of a share during the course of a particular time period (day, month or year), you would get a line that moves up and down sharply, like some demented saw blade. You might, however, be able to spot a general pattern underneath all that variation. The random variation is termed “noise” and the purpose of technical analysis is to remove that noise as far as possible.

Why doesn’t everybody use them?

No-one knows exactly how many organisations and individuals use ANNs to predict stock market prices as people tend to be secretive about their methods. One of the postulates of the Efficient Market Hypothesis is that information flows efficiently round stock markets and so any ANN that had a high success rate would, if made public knowledge, be quickly adopted by others. Essentially, this begs the question: Why spoil a good thing by making it generally available?

So perhaps the perfect neural network, that can predict every twist and turn in the market, is out there. If so, the chances are that you and I will never get to hear about it!

Are they any good? The simple answer is yes! Several scientific studies by leading universities in the United States such as Stanford, have shown that ANNs can give a distinct advantage over both experienced human stock traders and Expert Systems. In these studies, the neural networks are trained on past price changes in the stock market or currency market, and then their predictions are compared to subsequent prices to see if the advice they give is valid. It is not generally recorded whether the researchers have made any real money using them, possibly due to the ethical considerations that might arise from such speculation.

It won’t surprise you to learn that stock price prediction was one of the first uses of Artificial Intelligence, but in the early days, programmers tried to encode the sort of rules of thumb that human predictors used, such as “If the price of a share goes above a 7-point moving average, issue a buy signal.” Systems based on series of rules like this are called Expert Systems, and they have been used with some success. The main disadvantage that Expert Systems have compared to ANNs is that they require the rules to be explicitly programmed into them. These rules are often difficult to derive from stock predictors (many of whom seem to work on little more than instinct) and are subject to error and over-generalisation. ANNs, on the other hand, if given sufficient, typical training data, can derive the most suitable rules for themselves. On the other hand, ANNs are bad at describing those rules as they are stored in the form of numbers (weighted connection strengths). Expert systems can easily “explain” how they reached their conclusions.