One Parameter Selection Method of the BP Neural Network on Real Options Pricing

DOI

10.2991/lemcs-14.2014.170How to use a DOI?

Keywords

Real options pricing; BP neural network; Genetic algorithm; Parameters optimization;Prediction

Abstract

Based on the theory of BP neural network, the evaluation prediction model of real options pricing was established. Some quantized and non-quantized factors were all considered into the model such as evaluation value uncertainty, investment cost, investment opportunity duration, share degree, environment risk and so on. With one given example, the input parameters of the model were optimized by means of genetic algorithm and the detailed input parameters optimization process was also pointed out by dint of one calculation flow chart. The results show that the method not only guarantees the precision of calculation, but also reduces the number of input variables in the prediction model. At the same time, it can avoid that the calculation does not converge because of lots of input parameters to the prediction model. In addition, this can also reduce the subjectivity of the Black-Scholes model and make the evaluation of real options pricing more accurate. As a result, one good prediction effect has been obtained again.

Copyright

© 2014, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Lan Xiao
PY  - 2014/05
DA  - 2014/05
TI  - One Parameter Selection Method of the BP Neural Network on Real Options Pricing
BT  - Proceedings of the International Conference on Logistics, Engineering, Management and Computer Science
PB  - Atlantis Press
SP  - 744
EP  - 748
SN  - 1951-6851
UR  - https://doi.org/10.2991/lemcs-14.2014.170
DO  - 10.2991/lemcs-14.2014.170
ID  - Xiao2014/05
ER  -