|
Neural networks are composed of simple elements operating in parallel. These elements are inspired by biological nervous systems. As in nature, the network function is determined largely by the connections between elements. We can train a neural network to perform a particular function by adjusting the values of the connections (weights) between elements. Commonly neural networks are adjusted, or trained, so that a particular input leads to a specific target output. Such a situation is shown below. There, the network is adjusted, based on a comparison of the output and the target, until the network output matches the target. Typically many such input/target pairs are needed to train a network.
Batch training of a network proceeds by making weight and bias changes based on an entire set (batch) of input vectors. Incremental training changes the weights and biases of a network as needed after presentation of each individual input vector. Incremental training is sometimes referred to as "on line" or "adaptive" training. Neural networks have been trained to perform complex functions in various fields, including pattern recognition, identification, classification, speech, vision, and control systems.
The supervised training methods described above are used often, but other networks can be obtained from unsupervised training techniques or from direct design methods where training is not required. Unsupervised networks can be used, for instance, to identify groups of data. Certain kinds of linear networks and Hopfield networks are designed directly. In summary, there are a variety of kinds of design and learning techniques that enrich the choices that a user can make. Neural networks have a history of some six decades but have found solid application only in the past twenty years. The field is still developing rapidly. Thus, it is distinctly different from the fields of control systems or optimization, where the terminology, basic mathematics, and design procedures have been established and applied for many years
Technical Analysis is an approach that uses information of past stock behavior in order to forecast future price movements. Within the technical analysis community there exist several schools with different techniques, but they all have in common that they use price and volume history. A basic thought is that it takes time before the market reacts upon new information and that pattern often occur in price behavior which makes forecasting possible. Technical analysis makes judicious use of technical indicators for fair predicrion of required commodity.
A technical indicator is a series of data points that are derived by applying a formula to the price data of a security. Price data includes any combination of the open, high, low or close over a period of time. Some indicators may use only the closing prices, while others incorporate volume and open interest into their formulas. The price data is entered into the formula and a data point is produced. Thus, it offers a different perspective from which to analyze the price action. We will further elaborate on few specific indicators related to our software:
Momentum measures the speed of price change and provides a leading indicator of changes in trend. The Momentum line leads price action frequently enough to signal a potential trend reversal in the market.The indicators can warn of dormant strength or weakness in the price well ahead of the turning point. At extreme positive values, momentum implies an overbought position; at extreme negative values, an oversold position. A strongly trending market acts like a pendulum; the move begins at a fast pace, with strong momentum. It gradually slows down, or loses momentum, stops, and reverses course. The momentum line is always a step ahead of the price movement. It leads the advance or decline in prices and levels off while the current price trend is still in effect. It then begins to move in the opposite direction as prices begin to level off. The 10 day momentum line fluctuates on an open scale around a zero line. When the latest closing price is higher than that of 10 days ago, a positive value is plotted above the zero line. If the latest close is lower than 10 days previous, a negative value is plotted. Ten days or periods are usually used in calculating momentum, but any time period can be employed. The shorter the time frame used the more sensitive momentum becomes to short term fluctuations with more marked oscillations. Oscillator swings are smoother and more stable when a longer number of days are used.
Developed by J. Welles Wilder and introduced in his 1978 book, New Concepts in Technical Trading Systems, the Relative Strength Index (RSI) is an extremely useful and popular momentum oscillator. The RSI compares the magnitude of a stock's recent gains to the magnitude of its recent losses and turns that information into a number that ranges from 0 to 100. It takes a single parameter, the number of time periods to use in the calculation. In his book, Wilder recommends using 14 periods. Here is an example:
We see in the above example that, %K Readings below 20 are considered oversold and readings above 80 are considered overbought. However, Lane did not believe that a reading above 80 was necessarily bearish or a reading below 20 bullish. A security can continue to rise after the Stochastic Oscillator has reached 80 and continue to fall after the Stochastic Oscillator has reached 20. Lane believed that some of the best signals occurred when the oscillator moved from overbought territory back below 80 and from oversold territory back above 20. Buy and sell signals can also be given when %K crosses above or below %D. However, crossover signals are quite frequent and can result in a lot of whipsaws. One of the most reliable signals is to wait for a divergence to develop from overbought or oversold levels. Once the oscillator reaches overbought levels, wait for a negative divergence to develop and then a cross below 80. This usually requires a double dip below 80 and the second dip results in the sell signal. For a buy signal, wait for a positive divergence to develop after the indicator moves below 20. This will usually require a trader to disregard the first break above 20. After the positive divergence forms, the second break above 20 confirms the divergence and a buy signal is given.
Moving averages are one of the most popular and easy to use tools available to the technical analyst. They smooth a data series and make it easier to spot trends, something that is especially helpful in volatile markets. They also form the building blocks for many other technical indicators and overlays. The two most popular types of moving averages are the Simple Moving Average (SMA) and the Exponential Moving Average (EMA). all moving averages are lagging indicators and will always be "behind" the price. The price of EK is trending down, but the simple moving average, which is based on the previous 10 days of data, remains above the price. If the price were rising, the SMA would most likely be below. Because moving averages are lagging indicators, they fit in the category of trend following indicators. When prices are trending, moving averages work well. However, when prices are not trending, moving averages can give misleading signals.
The above four indicators give a rough idea of the variety of such indication mechanisms existing today for stock prediction. More the number of indicators, more complex and accurate is the prediction. In essence, today we are more technologically advanced in the field of forecasting those seemingly random stock markets.