This paper presents a time series forecasting methodology and applies it to generate one--step-- ahead predictions for the daily foreign exchange spot rates. The methodology draws from the disciplines of chaotic time series analysis, clustering, artificial neural networks and evolutionary computation. In brief, clustering is applied to identify neighborhoods in the reconstructed state space of the system; and subsequently neural networks are trained to model the dynamics of each neighborhood separately. The results obtained through this approach are promising.

this paper, the combination of unsupervised clustering algorithms with feedforward neural networks in exchange rate time series forecasting is studied. Unsupervised clustering algorithms have the desirable property of deciding on the number of partitions required to accurately segment the input space during the clustering process, thus relieving the user from making this ad hoc choice. Combining this input space partitioning methodology with feedforward neural networks acting as local predictors for each identified cluster helps alleviate the problem of non--stationarity frequently encountered in real--life applications. An improvement in the one--step--ahead forecasting accuracy was achieved compared to a global feedforward neural network model for the time series of the exchange rate of the German Mark to the US Dollar

and applies it to generate multiple--step--ahead predictions for the direction of change of the daily exchange rate of the Japanese Yen against the US Dollar. The proposed methodology draws from the disciplines of chaotic time series analysis, clustering, and artificial neural networks. In brief, clustering is applied to identify neighborhoods in the reconstructed state space of the system; and subsequently neural networks are trained to model the dynamics of each neighborhood separately. The results obtained through this approach are promising.

A successful financial prediction system presents many challenges. Some are encountered over again, and though an individual solution might be system-specific, general principles still apply. Using them as a guideline might save time, effort, boost results, as such promoting project’s success. This paper remarks on a prediction system development stemming from author’s experiences and published results. The presentation follows stages in a prediction system development: data preprocessing, prediction algorithm selection and boosting, system evaluation – with some commonly successful solutions highlighted. 1.

ii Hard problems force innovative approaches and attention to detail, their exploration often contributing beyond the area initially attempted. This thesis investigates the data mining process resulting in a predictor for numerical series. The series experimented with come from financial data – usually hard to forecast. One approach to prediction is to spot patterns in the past, when we already know what followed them, and to test on more recent data. If a pattern is followed by the same outcome frequently enough, we can gain confidence that it is a genuine relationship. Because this approach does not assume any special knowledge or form of the regularities, the method is quite general – applicable to other time series, not just financial. However, the generality puts strong demands on the pattern detection – as to notice regularities in any of the many possible forms. The thesis ’ quest for an automated pattern-spotting involves numerous data mining and optimization techniques: neural networks, decision trees, nearest neighbors, regression, genetic algorithms and other. Comparison of their performance on a stock exchange index data is one of the contributions. As no single technique performed sufficiently well, a number of predictors have been put together, forming a voting ensemble. The vote is diversified not only by different training data – as usually done – but also by a learning method and its parameters. An approach is also proposed how to speed-up a predictor fine-tuning. The algorithm development goes still further: A prediction can only be as good as the training data, therefore the need for good data preprocessing. In particular, new multivariate discretization and attribute selection algorithms are presented. The thesis also includes overviews of prediction pitfalls and possible solutions, as well as of ensemble-building for series data with financial characteristics, such as noise and many attributes. The Ph.D. thesis consists of an extended background on financial prediction, 7 papers, and 2 appendices. iii

Machines (RVM) were used to predict daily returns for an FX carry basket. Market observable exogenous variables known to have a relationship with the basket along with lags of the basket’s return were used as inputs into these methods. Combinations of these networks were used in a committee and simple trading rules based on this amalgamated output were used to predict when carry basket returns would be negative for a day and hence a trader should go short this long-biased asset. The effect of using the networks for regression to predict actual returns was compared to their use as classifiers to predict whether the following day’s return would be up or down. Assuming highly conservative estimates of trading costs, over the 10.5 year (2751 trading day) rolling out of sample period investigated, improvements of 120 % in MAR ratio, 110 % in Sortino and 80 % in Sharpe relative to the ‘Always In ’ benchmark were found. Furthermore, the extent of the maximum draw-down was reduced by 19 % and the longest draw-down period was 53% shorter.

The application of text mining in organizations is growing. Text classification, an important type of text mining problem, is characterized by a large attribute space and entails an efficient and effective attribute selection procedure. There are two general attribute selection approaches: the filter approach and the wrapper approach. While the wrapper approach is potentially more effective in finding the best attribute subset, it is cost-prohibitive in most text classification applications. In this paper, we propose a hybrid attribute selection approach that is both efficient and effective for text classification problems. We apply the proposed approach to detect and prevent Internet abuse in the workplace, which is becoming a major problem in modern organizations. The empirical evaluations we conducted using a variety of classification algorithms, indexing schemes, and attribute selection methods demonstrate the utility of the proposed approach. We found that combining the filter and wrapper approaches not only boosts the accuracies of text classifiers but also brings down the computational costs significantly.

Abstract: Artificial Neural Network (ANN) is widely used in business forecasting. ANN is a powerful forecasting tool. It is suitable for solving complex problems. Recently, ANN has been applied in many varieties of business decision making, such as bankruptcy forecasting, customer churning prediction, stock price forecasting, business process innovations, and systems development. In this study, we investigated the usefulness of the ANN model in forecasting success when implementing Enterprise Resource Planning (ERP) systems. We used an ANN method to compare the performance of three different models: ANN, Multivariable Discriminant Analysis (MDA), and Case-based Reasoning (CBR). Experimental results show that the ANN approach is a promising method for forecasting successful ERP implementation.

Finance and investing is the second most frequent business area of neural networks applications after production/operations. Although many research results show that neural networks can solve almost all problems more efficiently than traditional modeling and statistical methods, there are opposite research results showing that statistical methods in particular data samples outperform neural networks. Many papers on neural network applications on stock markets provide forecast only on existing stocks. However, many new stocks are being listed each year. Thus the aim of this study is to explore this relatively un-tapped region in the stock market and to investigate if neural networks can predict the returns of these IPOs. As for the prediction model, this study uses a proposed sequential learning Radial Basis Function (RBF) and this neural network aims to take advantage of the relationship between time series and firm specific information. Since IPOs have prior information of itself, the predicted values will be based on related time series and variables of the firm specific factors. Experimental results based on IPOs from the Singapore Stock Exchange are presented to evaluate the performance of the prediction. 1.

Abstract—Conventional neural network training methods find a single set of values for network weights by minimizing an error function using some gradient descent-based technique. In contrast, the Bayesian approach infers the posterior distribution of weights, and makes predictions by averaging the predictions over a sample of networks, weighted by the posterior probability of the network given the data. The integrative nature of the Bayesian approach allows it to avoid many of the difficulties inherent in conventional approaches. This paper reports on the application of Bayesian MLP techniques to the problem of predicting the direction in the movement of the daily close value of the Australian All Ordinaries financial index. Predictions made over a 13 year out-of-sample period were tested against the null hypothesis that the mean accuracy of the model is no greater than the mean accuracy of a coin-flip procedure biased to take into account non-stationarity in the data. Results show that the null hypothesis can be rejected at the 0.005 level, and that the t-test p-values obtained using the Bayesian approach are smaller than those obtained using conventional MLPs methods.