Neural Networks in Finance and Investing: Using Artificial Intelligence to Improve Real-world Performance
Robert R. Trippi, Efraim Turban
Irwin Professional Pub., 1996 - Business & Economics - 821 pages
Neural networks are revolutionizing virtually every aspect of financial & investment decision-making. Financial firms worldwide are using neural networks to forecast markets, analyze credit risks, & improve back-office operations. This completely updated version of the classic first edition of Neural Networks in Finance & Investing (Probus, 1993) offers a wealth of new material reflecting the latest developments in the field. For investment professionals seeking to maximize this exciting new technology, this handbook is the definitive information source. Highlights include: Neural network approaches to financial forecasting; Techniques of debt risk assessment; Neuralnetworks role in commodity markets trading.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Neural Network Fundamentals for Financial Analysts
A New Tool for Financial
Applying Neural Networks
38 other sections not shown
Other editions - View all
accuracy algorithm analytical review ANN model applications approach Artificial Neural Networks assets audit AUTOBOX average back-propagation bank bankrupt bankruptcy prediction Black-Scholes Black-Scholes formula bond ratings Box-Jenkins Cascor classification coefficients companies credit unions data set database decision delta-hedging developed discriminant analysis distress distribution efficient markets hypothesis error rates estimate evaluation example expert system Figure financial ratios firms forecasting function hidden layer hidden units IEEE inventory IPOs Journal learning rate linear loan logit MAPE method misclassification multiple discriminant analysis neural net neural nets neural network models neurons nonbankrupt nonlinear number of hidden optimal options out-of-sample output layer parameters patterns percent perceptron performance period problem procedure processing elements profit regression risk rule Rumelhart selected sigmoid sigmoid function signals simulation statistical stock price Table techniques test set training and testing training data training set Type II error values variables volatility weights