Neural Networks

Neural networks represent a field of study within the Artificial Intelligence area where researchers are studying a "biologically inspired" way of processing information. Neural networks have proven to be good at solving many real-world business problems, to include predicting bank failures, predicting stock price movements, predicting the ratings of corporate bonds, emulating mortgage underwriting judgments, predicting thrift failures, and predicting corporate bankruptcies. (Each of the highlighted topics is linked to a review of an article pertaining to that specific topic. These articles are summaries provided for an artificial intelligence class offered at the University of Mississippi.)

The predictive ability of neural networks falls into the forecasting area and can be best related to the auto-associative memory of certain neural networks. The method used for neural network prediction is call generalization (Dutta and Shekhar, 1989). Generalization is different from auto-associative memory in that once the network has been trained, new data is input for the network to predict the output. Neural networks typically consist of six primary components; processing elements (neurons), connections between neurons, adaptive coefficients of connections, transfer functions, learning laws and the overall transformation process. Structural and mathematical details of neural networks can be found in several books and/or papers, e.g. Rumelhart and McClelland (1986).

Development of a particular neural network involves determining the number of perceptrons to be used. This refers to the number of layers that will be contained in the network. Most generally, neural network models are comprised of an input layer, an output layer, and at least one hidden layer. The number of nodes that are available at each layer also needs to be decided. This is most generally based on the particular problem being addressed. Once the number of layers, and nodes within each layer, are determined, the neural network is trained on a set of data. The training phase involves providing data to the neural network along with the known outcome that resulted. After many iterations through the training data set, the neural network will learn the patterns that are present in the data. The neural network will converge on a pattern which is based on the least number of errors during prediction of the training data outcomes. Once training is complete, the neural network is ready for use.

Neural Networks in Accounting

With neural networks becoming a well known and reliable source for processing information, accountants will soon begin using this technology in accounting related problems. Some of the fore mentioned areas are ones in which accountants can use neural networks. Other areas that may be of interest to accountants include extraction of knowledge from accounting information, analytical review process, and financial statement analysis. The use of neural networks in accounting is definitely going to increase in the future.