Abstracts - faqs.org

Abstracts

Mathematics

Search abstracts:
Abstracts » Mathematics

How effective are neural networks at forecasting and prediction? A review and evaluation

Article Abstract:

An evaluation of 48 studies on the application of artificial neural networks to business forecasting and prediction was conducted to determine the effectiveness of their validation and implementation. Results showed that 11 of the studies were both effectively validated and implemented, while another 11 were effectively validated and yielded favorable results, but some problems were detected with their implementation. Eighteen of these 22 studies affirm the potential of artificial neural networks for forecasting and prediction.

Author: Adya, Monica, Collopy, Fred
Publisher: John Wiley & Sons, Inc.
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 1998
Forecasting, Models, Computer networks, Evaluation, Neural networks, Business forecasting

User Contributions:

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

CAPTCHA


Causal forces: structuring knowledge for time-series extrapolation

Article Abstract:

A technique for structuring domain knowledge for use in quantitative extrapolation represents causal forces as inputs, since this can result in greater savings, accuracy and judgment integration than standard extrapolation methods. This technique is unique because it does not incorporate the common but unwise assumption that causal forces support trends. Instead, an inserted selection rule forbids trends from being extrapolated when they are contrary tocausal force directions.

Author: Armstrong, J. Scott, Collopy, Fred
Publisher: John Wiley & Sons, Inc.
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 1993
Usage, Forecasts and trends, Time-series analysis, Time series analysis, Rule-based systems, Rule based systems, Causality (Physics)

User Contributions:

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

CAPTCHA


Correspondence on the selection of error measures for comparisons among forecasting methods

Article Abstract:

A study criticizing the selection of error measures for comparisons among forecasting methods was conducted. The Generalized Forecast Error Second Moment is not an improvement over the Mean Square Error in forecasting performance because forecast accuracy may be determined by other criteria. Also, simulated data used in the proof of the method were not a good representation of actual data.

Author: Armstrong, J. Scott, Fildes, Robert A.
Publisher: John Wiley & Sons, Inc.
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 1995
Methods, Forecasting, Error analysis (Mathematics)

User Contributions:

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

CAPTCHA


Subjects list: Research
Similar abstracts:
  • Abstracts: An assessment of the relative importance of real interest rates, inflation, and term premiums in determining the prices of real and nominal U.K. bonds
  • Abstracts: On the subdifferential of the value function in economic optimization problems. Existence of equilibria in the presence of increasing returns: a synthesis
  • Abstracts: Existence and properties of a value allocation for an economy with differential information. Uniform continuity of information combination: a corrigendum
  • Abstracts: Preference for flexibility in a savage framework. Maximization and the act of choice. Internal consistency of choice
  • Abstracts: Epistemic conditions for Nash equilibrium. Learning, mutation, and long run equilibria in games. Reputation and equilibrium characterization in repeated games with conflicting interests
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.