Abstracts - faqs.org

Abstracts

Business, general

Search abstracts:
Abstracts » Business, general

A primer on neural networks for forecasting

Article Abstract:

Artificial neural network models, which are flexible nonlinear models, are gaining acceptance in the electric utility industry for short-term forecasting. With the neural network's framework, a flexible function that can estimate a variety of nonlinear processes is achieved. Neural networks also offer substantial advantages in forecasting problems where nonlinearities and variable interactions play a vital role. However, confusion and controversy plague the topic of neural networks, which partly reveal that a different language is used for neural networks compared to what is used in the more popular area of econometrics.

Author: McMenamin, J. Stuart
Publisher: Graceway Publishing Company Inc.
Publication Name: Journal of Business Forecasting
Subject: Business, general
ISSN: 0278-6087
Year: 1997
Electronic computers, Electronic Computer Manufacturing, Artificial Intelligence Systems, Electric utilities, Forecasts and trends, Interview, Artificial intelligence, Nonlinear programming

User Contributions:

Comment about this article or add new information about this topic:

CAPTCHA


A neural network approach to forecasting financial distress

Article Abstract:

The use of neural network (NN) computing systems is said to be more reliable than the multiple discriminant analysis (MDA) approach in determining the financial health of firms. A study was conducted to confirm this assertion. Two sets of studies were made, with each set having 47 healthy and 47 financially distressed firms as subjects. The first set used only NN while the second one used both NN and MDA. Findings revealed that NN is truly more accurate than MDA in determining financial standing of firms.

Author: Coats, Pamela K., Fant, L. Franklin
Publisher: Graceway Publishing Company Inc.
Publication Name: Journal of Business Forecasting
Subject: Business, general
ISSN: 0278-6087
Year: 1991
Software, Finance, Financial software, Business enterprises

User Contributions:

Comment about this article or add new information about this topic:

CAPTCHA


Neural networks vs. conventional methods of forecasting

Article Abstract:

Neural network forecasting can outperform most types of conventional forecasting models. In neural networks, relevant examples are programmed and assimilated to develop underlying relationships that can be learned by a network. Relationships do not have to be specified in advance in such networks, and they also do not require assumptions regarding underlying population distributions.

Author: Kuo, Chin, Reitsch, Arthur
Publisher: Graceway Publishing Company Inc.
Publication Name: Journal of Business Forecasting
Subject: Business, general
ISSN: 0278-6087
Year: 1995
Methods

User Contributions:

Comment about this article or add new information about this topic:

CAPTCHA


Subjects list: Usage, Computer networks, Neural networks, Business forecasting
Similar abstracts:
  • Abstracts: A general theory of network governance: exchange conditions and social mechanisms. The knowledge-based view, nested heterogeneity, and new value creation: Philosophical considerations on the locus of knowledge
  • Abstracts: Computers get powerful 'hearing' aids: improved methods of voice recognition. Standards set for data-voice phone service
  • Abstracts: Marketing. New business concepts for growth. Marketing led strategic change
  • Abstracts: An analytic process model of two-party negotiations. Calculating the reserve for a time and usage indexed warranty
  • Abstracts: Diversification and performance: critical review and future directions. A cognitive model of CEO dismissal: understanding the influence of board perceptions, attributions and efficacy beliefs
This website is not affiliated with document authors or copyright owners. This page is provided for informational purposes only. Unintentional errors are possible.
Some parts © 2025 Advameg, Inc.