Estimating the performance of Sino‐Hong Kong joint ventures using neuralnetwork ensembles

Abstract

Prediction of the 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 1,463 Sino‐Hong Kong joint ventures were gathered and those that appeared on the Honor Roll of the China Association of Enterprises with Foreign Investment are identified. Neural network models were used to relate the posterior probability ‐ the probability that a venture gets on the Honor Roll ‐ and the seven economic variables. A simple and yet powerful method called the ensemble method was used to estimate the posterior probability. The results indicate that every variable, except one, has influence on the probability of success. Perhaps more important, the results demonstrate that the modeling approach is able to mine useful information from the data set.