Financial and economic forecasters have spurted the recent development of a number of new forecasting models. In the hard sciences, `neural network' can be used in the context of statistical analysis such as regression analysis, time series analysis, moving averages, and smoothing methods, and numerous judgmental methods as an alternative. In addition, neural networks can also overcome many of the shortcomings of traditional techniques, analyzing noisy data and incomplete data.

Neural networks are patterned after the parallel processing methods of the human brain. The biological brain is composed of billions of interconnected processing elements called neurons, which transmit information and strengthen when the brain learns.

Although the brain is slower than traditional computers in numeric calculations, the human brain can abstract and generalize data instantly on problems a conventional computer could not even understand. Neural networks use interconnected processing elements governed by algorithms that allow them to learn from mistakes, recognize patterns in noisy data, and operate with incomplete information.

By emulating the processing capabilities of the human brain, neural networks attempt to overcome the limitations of traditional computers. An artificial neural network (ANN) is a model composed of several highly interconnected computational units called neurons or nodes. Each node performs a simple operation on an input to generate an output that is forwarded to the next node in the sequence. This parallel processing allows for great advantages in data analysis.

Applied Finance Journal, Mutual Funds, Regression Analysis, Statistical Analysis, Time Series Analysis, Neural Networks, Artificial Neural Network, Backpropagation Algorithm, Machine Intelligence, Neural Network Technique, Multi Layer Perceptron.