Abstract — Three networks are compared for low false alarm stock trend predictions. Short-term trends, particularly attractive for neural network analysis, can be used profitably in scenarios such as option trading, but only with significant risk. Therefore, we focus on limiting false alarms, which improves the risk/reward ratio by preventing losses. To predict stock trends, we exploit time delay, recurrent, and probabilistic neural networks (TDNN, RNN, and PNN, respectively), utilizing conjugate gradient and multistream extended Kalman filter training for TDNN and RNN. We also discuss different predictability analysis techniques and perform an analysis of predictability based on a history of daily closing price. Our results indicate that all the networks are feasible, the primary preference being one of convenience. Index Terms—Conjugate gradient, extended Kalman filter, financial engineering, financial forecasting, predictability analysis, probablistic neural network, recurrent neural network, stock market forecasting, time delay neural network, time series analysis, time series prediction, trend prediction. I.

Abstract not found

This paper presents a novel Fourier analysis-based technique to aggregate, transmit, and visualize decision trees in a mobile environment. Fourier representation of a decision tree has several interesting properties that are particularly useful for mining continuous data streams from small mobile computing devices. This paper presents algorithms to compute the Fourier spectrum of a decision tree and the vice versa. It offers a framework to aggregate decision trees in their Fourier representations. It also describes MobiMine, a mobile data mining system for mining stock-market data from handheld devices connected over low-bandwidth wireless networks.

This paper describes a novel approach to detect correlation from data streams in the context of MobiMine --- an experimental mobile data mining system. It presents a brief description of the MobiMine and identifies the problem of detecting dependencies among stocks from incrementally observed financial data streams. This is a non-trivial problem since the stock-market data is inherently noisy and small incremental volumes of data makes the estimation process more vulnerable to noise.

In this paper, the concept of a long memory system for forecasting is developed. Pattern Modelling and Recognition Systems are introduced as local approximation tools for forecasting. Such systems are used for matching current state of the time-series with past states to make a forecast. In the past, this system has been successfully used for forecasting the Santa Fe competition data. In this paper, we forecast the financial indices of six different countries and compare the results with neural networks on five different error measures. The results show that pattern recognition based approaches in time-series forecasting are highly accurate and these are able to match the performance of advanced methods such as neural networks. 3 1. MOTIVATION Time-series forecasting is an important research area in several domains. Traditionally, forecasting research and practice has been dominated by statistical methods. More recently, neural networks and other advanced methods on prediction have ...

We describe an end-to-end real-time S&P futures trading system. Inner-shell stochastic nonlinear dynamic models are developed, and Canonical Momenta Indicators (CMI) are derived from a fitted Lagrangian used by outer-shell trading models dependent on these indicators. Recursive and adaptive optimization using Adaptive Simulated Annealing (ASA) is used for fitting parameters shared across these shells of dynamic and trading models.

Decision Support System (MDSS), specifically, by discovering important variables that influence sales performance of colour television (CTV) sets in the Singapore market using neural networks. Three kinds of variables, expert knowledge, marketing information and environmental data, are examined. The information about the effects of each of these variables has been studied and made available for decision making. However, their combined effect is unknown. This study attempts to explore the combined effect for the benefit of our collaborator, a multinational corporation (MNC) in the consumer electronics industry in Singapore. Putting these three variables together as input variables results in a neural network model. Neural network training is conducted using historical data on CTV sales in Singapore collected over the past one and a half years. Sensitivity analysis is then performed to reduce input variables of neural networks. This is done by analyzing the weights of the input node connections in the trained neural networks using two different methods. The weaker variables can be excluded, and this results in a simpler model. Further, an R-Square value of almost 1 is obtained through the inclusion of an Unknown variable when the network model consisting only of the most influential variables is trained and tested. Knowing the most influential variables, which in this case include Average Price, Screen Size, Stereo Systems, Flat-Square screen type and Seasonal Factors, marketing managers can improve sales performance by paying more attention

In this paper, two local approximation techniques for prediction are explored. First, a pattern recognition technique called Pattern Modelling and Recognition System (PMRS) is explored for making multiple forecasts. We then describe a single nearest neighbour based prediction system for multiple forecasting. Both models are based on using local neighbourhoods in data for making prediction. Multiple prediction profiles are generated and analysed for four time-series data. These multiple forecasts define a predicted behavioural profile of given univariate systems. The predicted profiles are compared against the actual behaviour of the studied systems on a number of proposed error measures. The results show that local approximation used in the two models for making multiple forecasts is an important method of profiling the true behaviour of univariate systems. Keywords Pattern Recognition and Modelling System Multiple Forecasting Behaviour Profiling Nearest Neighbours Time-Series Predi...

Abstract not found

In the last decade, bio-inspired methods have gained an increasing acceptation as alternative approaches for Time Series Forecasting. Indeed, the use of tools such as Artificial Neural Networks (ANNs) and Genetic and Evolutionary Algorithms (GEAs), introduced important features to forecasting models, taking advantage of nonlinear learning and adaptive search. In the present approach, a combination of both paradigms is proposed, where the GEA's searching engine will be used to evolve candidate ANNs topologies, enhancing forecasting models that show good generalization capabilities. A comparison was performed, contrasting bio-inspired and conventional methods, which revealed better forecasting performances, specially when more difficult series were taken into consideration; i.e., nonlinear and chaotic ones.