Improving the pricing of options: a neural network approach
Article Abstract:
Parsimonious neural networks with excellent out-of-sample performance compared to the Black/Scholes model are generated from statistical specification strategies, affirming the latter's successful application in improving the pricing of the options through neural networks. This was concluded from the application of statistical inference techniques to the construction of neural network models which can explain the prices of call options on the German stock index Deutscher Aktien Index. Results affirm the use of statistical methods for model specification and inference in neural networks.
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 1998
User Contributions:
Comment about this article or add new information about this topic:
Predicting LDC debt rescheduling: performance evaluation of OLS, logit, and neural network models
Article Abstract:
Various mathematical models are tested to determine their value in forecasting debt rescheduling for developing countries. Newer models, such as neural networks, are as effective as older models, such as ordinary least squares and logits.
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 2001
User Contributions:
Comment about this article or add new information about this topic:
A neural network versus Black-Scholes: a comparison of pricing and hedging performances
Article Abstract:
The superiority of neural network models for hedging and pricing derivative securities is discussed.
Publication Name: Journal of Forecasting
Subject: Mathematics
ISSN: 0277-6693
Year: 2003
User Contributions:
Comment about this article or add new information about this topic: