Using Neural Networks To Predict The Performance of Sino-Foreign Joint Ventures

An arti...cial neural network model is used to predict the performance of Sino-foreign joint ventures. Performance of international joint ventures remains a relatively under-researched area, yet its importance is well recognized due to the tremendous surge in joint venture activities in the past decade. Data on 2,416 Sino-foreign joint ventures was gathered, allowing for empirical analysis using neural networks and traditional approaches such as logistic regression. The results show that neural networks are indeed a viable approach to modeling the performance of joint ventures. This study identi...es and examines the e¤ects of key parameters in neural networks for such modeling e¤orts. Moreover, in comparison to logistic regression, neural networks provided better results in classi...cation. This paper also attempts to provide a basis upon which neural networks can be used for the purpose of variable selection in statistical modeling.