How effective are neural networks at forecasting and prediction? A review and evaluation
✍ Scribed by Monica Adya; Fred Collopy
- Publisher
- John Wiley and Sons
- Year
- 1998
- Tongue
- English
- Weight
- 167 KB
- Volume
- 17
- Category
- Article
- ISSN
- 0277-6693
No coin nor oath required. For personal study only.
✦ Synopsis
Despite increasing applications of arti®cial neural networks (NNs) to forecasting over the past decade, opinions regarding their contribution are mixed. Evaluating research in this area has been dicult, due to lack of clear criteria. We identi®ed eleven guidelines that could be used in evaluating this literature. Using these, we examined applications of NNs to business forecasting and prediction. We located 48 studies done between 1988 and 1994. For each, we evaluated how eectively the proposed technique was compared with alternatives (eectiveness of validation) and how well the technique was implemented (eectiveness of implementation). We found that eleven of the studies were both eectively validated and implemented. Another eleven studies were eectively validated and produced positive results, even though there were some problems with respect to the quality of their NN implementations. Of these 22 studies, 18 supported the potential of NNs for forecasting and prediction.