Neural Networks and the Financial Forecasting: A Review
Published in IEEE Conference on Cognizance of Applied Engineering & Research , 2013
Authors: Karan Wanchoo
An overview of the artificial neural network basics and operation, architectures, and the major algorithms used for training the neural network models are presented in this paper. Till date, neural networks have made many useful contributions to solve theoretical and practical problems in finance related areas. We see that while the main strength of Neural Networks is embedded in its non-linearity and data-driven aspects, its main shortcoming relates to the lack of explanation power in the trained networks due to the complex structure of the networks. Further, a brief review of artificial neural network applications in finance concerned areas has been discussed. It has been observed that in finance domain significant applications are in trading and forecasting such as future price estimation, foreign exchange rate forecasting, corporate bankruptcy prediction, fraud detection etc. A wide range of software based on ANNs is available today offering solutions to a number of financial problems. However, focus remains on improvement of accuracy of prediction by these networks.