Bond rating: a nonconservative application of neural networks
- 1 January 1988
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 443-450 vol.2
- https://doi.org/10.1109/icnn.1988.23958
Abstract
The authors apply neural networks to a generalization problem of predicting the ratings of corporate bonds, where conventional mathematical modeling techniques have yielded poor results and it is difficult to build rule-based artificial-intelligence systems. The results indicate that neural nets are a useful approach to generalization problems in such nonconservative domains, performing much better than mathematical modeling techniques like regression.<>Keywords
This publication has 5 references indexed in Scilit:
- Connectionist expert systemsCommunications of the ACM, 1988
- Learning representations by back-propagating errorsNature, 1986
- An Alternative Approach to Predicting Corporate Bond RatingsJournal of Accounting Research, 1970
- What's in a Bond RatingJournal of Financial and Quantitative Analysis, 1969
- The Determination of Long-Term Credit Standing with Financial RatiosJournal of Accounting Research, 1966