You are on page 1of 4


It is nowadays a common notion that vast amounts of capital are traded through the Stock Markets all around the world. National economies are strongly linked and heavily influenced of the performance of their Stock Markets. Moreover, recently the Markets have become a more accessible investment tool, not only for strategic investors but for common people as well. Consequently they are not only related to macroeconomic parameters, but they influence everyday life in a more direct way. Therefore they constitute a mechanism which has important and direct social impacts. The characteristic that all Stock Markets have in common is the uncertainty, which is related with their short and long-term future state. This feature is undesirable for the investor but it is also unavoidable whenever the Stock Market is selected as the investment tool. The best that one can do is to try to reduce this uncertainty. Stock Market Prediction (or Forecasting) is one of the instruments in this process. The financial market is a complex, evolutionary, and non-linear dynamical system. The field of financial forecasting is characterized by data intensity, noise, non-stationary, unstructured nature, high degree of uncertainty, and hidden relationships. Many factors interact in finance including political events, general economic conditions, and traders’ expectations. Therefore, predicting finance market price movements is quite difficult. Increasingly, according to academic investigations, movements in market prices are not random. Rather, they behave in a highly nonlinear, dynamic manner. In literature a number of different methods have been applied in order to predict Stock Market returns. These methods can be grouped in four major categories: i) Technical Analysis Methods, ii) Fundamental Analysis Methods, iii) Traditional Time Series Forecasting and iv) Machine Learning Methods. Technical analysts, known as chartists, attempt to predict the market by tracing patterns that come from the study of charts which describe historic data of the market. Fundamental analysts study the intrinsic value of an stock and they invest on it if they estimate that its current value is lower that its intrinsic value. In Traditional

Data collection: The historical data is obtained the from the finance section of Yahoo and the National Stock Exchange. The network consist of consists of N input nodes. The whole data set covers a total of 676 pairs of observations. K hidden nodes and M output nodes. and ω nk km is the network weight for hidden node k is the network weight for input node n and hidden node . There is a sufficient number of hidden nodes. This means that if such patterns exist. Assume ω and output node m. The second part contains 36 pairs of observations which are reserved for evaluation and comparison of performances among forecasting models. an empirical study on building a stock buying or selling is predicted using a feed-forward Back propagation network. These linear models are divided in two categories: the univariate and the multivariate regression models. approximate any continuous nonlinear function. It is trained and tested with past price data from National Stock Exchange. The first part consists 640 pairs of observations are used to determine the specifications of the models and parameters. Let opm and opk be the output of output node m and hidden node k from input pattern p. Model 1: Back propagation Model: In this section. There are a number of methods that have been developed under the common label Machine Learning and these methods use a set of samples and try to trace patterns in it (linear or non-linear) in order to approximate the underlying function that generated the data.Time Series forecasting an attempt to create linear prediction models to trace patterns in historic data takes place. Finally. An appropriate network topology is selected. An appropriate learning rate and momentum are used. in principle. A multilayer perceptron (MLP) with a sufficient number of hidden nodes can. artificial Neural Network has taken a great prominent role in forecasting the share market and a number of researches haven done in this area. depending on whether they use one of more variables to approximate the Stock Market time series. a BPN can be trained to ‘‘discover’’ the patterns provided that: • • • • A sufficient amount of appropriate data is available to train the BPN. respectively. The data set is divided into two parts.

Use the desired target tp = { tp1. ………….k. Step 2: Forward Pass: Select the input pattern xp = { xp1. then the algorithm is completed and the convergence is achieved. Choosing the network architecture and specifying the training algorithm. Determining the training and testing strategy.y. this feature makes the BPN an attractive candidate for prediction tasks. E(i). The standard algorithm for BPN is as follow: Step 1: Initialization: Initialize all weights and refer to them as current weight ω km (0) and ω nk. Obviously. Step 3: Backward Pass: Compute the changes of the weights for the next iteration ∆ ω BPN system: • • • • • • Defining the output goal. let xpn be the input value in input node n for input pattern p. Determining the optimum network topology. If E(i) <= E. km (i +1) and ∆ ω nk (i +1). Determining the proper input data and necessary preprocessing. go to step 3 (Backward Pass). Set the learning rate µ and the momentum factor α to small positive values (e. Set the error threshold E and the iteration number i = 0. x pn} from the training set and compute opm (i) and opk . the following issues need to be considered during the design of a The major benefit of the BPN is that it is capable of learning the nonlinear mapping between the inputs and outputs by using an appropriate network topology and given a sufficient amount of training data. Evaluating the results.1). The major presumption of technical analysis is that history repeats itself and that trends and patterns exist in the price data. the BPN can also produce an acceptable output for some unseen data. otherwise. Note that the symbol ∆ represents the difference between the current and the new value in the next iteration. Once the underlying mapping has been learnt sufficiently well. tpm } associated with xp to compute the sum of the squared system error. for all input patterns. Also. A traditional technical analyst tries to identify these patterns by examining price charts and technical indicators. If . In general. 0. and tpm be the target output value in the output node m for input pattern p.g.

both long and short [50] Skabar. if the training set is too small. financial trading and the efficient market hypothesis. as described in Skabar and Cloete (2002)[50]. Cloete. The basic input data includes raw data such as the daily open. The disadvantage of this BPN is care must be taken in choosing the appropriate size of the training set. In fact. term. was adopted for training and testing.n-day moving averages and momentum. low and close prices. A moving-windows approach. but it will not predict with acceptable accuracy because the network is unable to learn the underlying patterns sufficiently well with such a limited amount of data. among others. 2002. and trading volumes and in addition. Neural networks.such patterns are identified. The training and testing strategy is probably the most important issue in designing a BPN. even if the network can converge. Australian Computer Science Communications 24 (1). it may have learned some historical patterns that may no longer be effective because the market conditions have already changed too drastically. the following is also be considered : Fundamental factors P/E ratios and dividend yield. if the training set is too large. which is the buy or sell trading signal. I.. Moreover. On the other hand. will converge easily. high. he or she can presumably predict the future price movements. it will be more difficult for the network to converge.. Interest rates . Model 2: Radial Basis Neural Network Technical indicators . A. A single output. On one hand. . sometimes it fails to converge at all. dividend payment. 241–249.