We introduce a method for deriving a metric, locally based on the Fisher information matrix, into the data space. A Self-Organizing Map is computed in the new metric to explore financial statements of enterprises. The metric measures local distances in terms of changes in the distribution of an auxiliary random variable that reflects what is important in the data. In this paper the variable indicates bankruptcy within the next few years. The conditional density of the auxiliary variable is first estimated, and the change in the estimate resulting from local displacements in the primary data space is measured using the Fisher information matrix. When a Self-Organizing Map is computed in the new metric it still visualizes the data space in a topology-preserving fashion, but represents the (local) directions in which the probability of bankruptcy changes the most.

Despite increasing applications of artificial neural networks (NNs) to forecasting over the past decade, opinions regarding their contribution are mixed. Evaluating research in this area has been difficult, due to lack of clear criteria. We identified eleven guidelines that could be used in evaluating this literature. Using these, we examined applications of NNs to business forecasting and prediction. We located 48 studies done between 1988 and 1994. For each, we evaluated how effectively the proposed technique was compared with alternatives (effectiveness of validation) and how well the technique was implemented (effectiveness of implementation). We found that eleven of the studies were both effectively validated and implemented. Another eleven studies were effectively validated and produced positive results, even though there were some problems with respect to the quality of their NN implementations. Of these 22 studies, 18 supported the potential of NNs for forecasting and prediction.

This paper presents an overview of the di!erent types of neural network models which are applicable when solving business problems. The history of neural networks in business is outlined, leading to a discussion of the current applications in business including data mining, as well as the current research directions. The role of neural networks as a modern operations research tool is discussed. Scope and purpose Neural networks are becoming increasingly popular in business. Many organisations are investing in neural network and data mining solutions to problems which have traditionally fallen under the responsibility of operations research. This article provides an overview for the operations research reader of the basic neural network techniques, as well as their historical and current use in business. The paper is intended as an introductory article for the remainder of this special issue on neural networks in business. # 2000 Elsevier Science Ltd. All rights reserved. Keywords: N...

statistical methods?

Artificial neural networks have been used to support applications across a variety of business and scientific disciplines during the past years. Artificial neural network applications are frequently viewed as black boxes which mystically determine complex patterns in data. Contrary to this popular view, neural network designers typically perform extensive knowledge engineering and incorporate a significant amount of domain knowledge into artificial neural networks. This paper details heuristics that utilize domain knowledge to produce an artificial neural network with optimal output performance. The effect of using the heuristics on neural network performance is illustrated by examining several applied artificial neural network systems. Identification of an optimal performance artificial neural network requires that a full factorial design with respect to the quantity of input nodes, hidden nodes, hidden layers, and learning algorithm be performed. The heuristic methods discussed in this paper produce optimal or near-optimal performance artificial neural networks using only a fraction of the time needed for a full factorial design. Keywords: Artificial neural networks; Heuristics; Input vector; Hidden layer size; ANN learning method; Design. Heuristics Principles for the Design of Artificial Neural Networks - Page 3 1.

Abstract not found

Experimental comparisons between statistical and machine learning methods appear with increasing frequency in the literature. However, there does not seem to be a consensus on how such a comparison is performed in a methodologically sound way. Especially the effect of testing multiple hypotheses on the probability of producing a "false alarm" is often ignored. We transfer multiple comparison procedures from the statistical literature to the type of study discussed in this paper. These testing procedures take the number of tests performed into account, thereby controlling the probability of generating "false alarms". The multiple comparison procedures selected are illustrated on well-known regression and classification data sets. 26.1 Introduction Recent interactions between the statistical and artificial intelligence communities (see e.g. [Han93, CO94]), have led to many studies that compare the performance of empirical statistical and machine learning methods on real-life data sets; ...

Neural networks and machine learning methods have proved in many ways and in a number of publications to be real challengers to statistical methods - especially to logit and discriminant analysis - in predicting failures. However, most of the studies have used a rather small data set, very often close to only one hundred observations. Therefore, it has been difficult to say whether there are any significant differences between the methods tested. In this study, we compare neural networks, a machine learning method, discriminant analysis and logit analysis using a large data set consisting of 570 companies. We investigate the effects of the prediction capabilities of the methods when using different sample sizes for estimation and testing, i.e., 400-170, 200-90 and 100-50. Our study shows that neural networks and the machine learning method perform better than discriminant analysis and logit analysis when the sample size is 400 while there is no best performer when the sample size is de...

Neural networks have proved in many ways and in a number of publications to be real challengers to statistical methods - especially to logit analysis - in predicting failures. However, most of the studies have used a rather small data set, very often close to only one hundred observations. Therefore, it has been difficult to say whether there are any significant differences between the methods tested. In this study, we extend a previous study and compare rule-based learning with neural networks and logit analysis using a larger data set consisting of 570 companies. We investigate the effects of the prediction capabilities of the methods using different sample sizes and different time periods for estimation. Our study shows that in this domain neural networks and rule-based learning perform better than logit analysis, but there is substantial variation in the results depending on the sample size and time period. Introduction 1 Analysing data with different methods has recently gained ...

Ability to forecast market variables is critical to analysts, economists and investors. Among other uses, neural networks are gaining in popularity in forecasting market variables. They are used in various disciplines and issues to map complex relationships. We present a primer for using neural networks for forecasting market variables in general, and in particular, forecasting volatility of the S&P 500 Index futures prices. We compare volatility forecasts from neural networks with implied volatility from S&P 500 Index futures options using the Barone-Adesi and Whaley (BAW) model for pricing American options on futures. Forecasts from neural networks outperform implied volatility forecasts. Volatility forecasts from neural networks are not found to be significantly different from realized volatility. Implied volatility forecasts are found to be significantly different from realized volatility in two