Neural Networks

Paper Summary:

This paper explains that a computer science phenomenon called neural networks, similar to the part of the brain, consist of ways to connect information to produce output that is consistent with the processes. The author points out that recent interest in neural models stems primarily from its nonlinear models that can be trained to map past and future values of the input-output relationship, thus extracting relationships between the data that were not obvious using other analytical tools. The paper stresses that, unlike conventional computers, neural networks have the unique capability of learning. The author relates that the fact that neural networks are trained without the restriction of a model to derive parameters and discover relationships, driven and shaped solely by the nature of the data, has profound implications and applicability to the finance field. The paper includes equations.

Table of Contents:
What are Neural Networks?
Figure 1: Neural Networking and Similarities with the Workings of the Human Brain
The History of Neural Networks
Figure 2: Multilayered Neural Network Model adapted from Stergiou and Siganos
Why Use Neural Networks?
Neural Networks Versus Conventional Computers
Figure 2a: Multilayer Perceptron Neural Network
Neural Networks in Finance
Time Series Analysis
Figure 3: Stock Market Data from the New York Stock Exchange for Newmont Mining: Random Walk?
Stock Market Analysis
Capital Budgeting and Risk
Figure 4: General Modeling of Neural Networks for Financial Capital Markets (Inclusive of Capital Budgeting and Risk Analysis)
Financial Forecasting
The Future of Neural Networks: A Critical Review

From the Paper:

"Capital budgeting is one of the most important functions of financial management. It encompasses a process of planning expenditures on assets whose cash flows are expected to extend beyond one year. A company with growth rates and profit margins such as that are dictated by capital expenditure and investment cannot afford to ignore the importance of capital budgeting. Erroneous forecasts of asset requirements can have serious consequences, Therefore there is always a need for complex and accurate models to dictate the relationship between variables."

Sample of Sources Used:

• "Financial Time Series as Random Walks". Extracted on March 5, 2007 from http://www.cs.sunysb.edu/~skiena/691/lectures/lecture8.pdf
• Gordon, Myron. The Investment, Financing, and Valuation of the Corporation. Irwin, 1962
• Lendasse, A.,Bodt, E., Wertz, V., and Verlesen, M. "Non-Linear Financial Time Series Forecasting - Application to the Bel 20 Stock Index". European Journal of Economic and Social Systems, 14 (1), 2000, 81-98. Retrieved on March 5, 2007 from http://www.edpsciences.org/articles/ejess/pdf/2000/01/verleyse.pdf?access=ok
• Smith, Leslie. "An Introduction to Neural Networks". Centre for Cognitive and Computational Neuroscience. April 2, 2003. Retrieved on March 6, 2007 from http://www.cs.stir.ac.uk/~lss/NNIntro/InvSlides.html
• Stasoft Incorporated. "Neural Networks". Stasoft.Com, 1984-2003. Retrieved on March 6, 2007 from http://www.statsoft.com/textbook/stneunet.html#index

More papers on Neural Networks:

• Term Paper # 132180 : "Neural Networks"
• Essay # 29155 : "Neural Networks"
• Analytical Essay # 61408 : "Expert Systems and Neural Networks"

APA Citation:

MLA Citation: