Artificial neural networks in bankruptcy prediction: general framework and cross-validation analysis

Article Abstract:

A cross-validation technique is employed to analyze the performance of neural networks in bankruptcy prediction. Cross-validation is a resampling approach that employs multiple random training and subsamples. In this method, all observations or patterns in the available sample are applied for testing and most of them are also employed for training the model. Further, the cross-validation technique will produce useful insights on the reliability of the neural networks in relation to sampling variation.

Methods, Computer networks, Forecasts and trends, Economic forecasting, Statistical sampling, Sampling (Statistics), Bankruptcy

---

Modeling foreign equity control in Sino - foreign joint ventures with neural networks

Article Abstract:

The artificial neural networks are employed to model the equity control in the joint ventures between China and other foreign countries. The neural networks offer due to their non - linear structure more accurate figures in the equity ownership percents.

China, Foreign trade, Foreign investments, International trade, Joint ventures

---

Explaining consumer choice through neutral networks: the stacked generalization approach

Article Abstract:

Models of neural networks, which examine the impact of demographic factors and consumer choice on firm's performance, are proposed.

Europe, Consumer preferences

Similar abstracts:

• Abstracts: Managerial assessments of export performance: conceptual framework and empirical illustration. Export market expansion strategies of direct-selling small and medium-sized firms: implications for export sales management activities
• Abstracts: Renewal reward processes with fuzzy rewards and their applications to T-age replacement policies. The fuzzy estimators of fuzzy parameters based on fuzzy random variables
• Abstracts: Evaluating and selecting e-commerce software and communication systems for a supply chain

This website is not affiliated with document authors or copyright owners. This page is provided for informational purposes only. Unintentional errors are possible.