Computational intelligence to model the export behavior of multinational corporation subsidiaries in Malaysia

The academic literature suggests that the extent of exporting by multinational corporation subsidiaries (MCSs) depends on their strategic role in the multinational corporation (MNC), their age and size, and whether their products are targeted at niche or commodity markets. In particular, it is claimed that MNCs seek to invest in a particular country if its resources adopt a vertically integrated structure, if the country grants regional or global sales mandates to their subsidiaries, or if it has been established in a host market for a longer time and is thus more likely to promote subsidiary exports. Our aim in this article is to model the complex export pattern behavior of multinational corporation subsidiaries in Malaysia using a Takagi–Sugeno fuzzy inference system. The proposed fuzzy inference system (FIS) is optimized by using neural network learning and evolutionary computation. Empirical results clearly show that the proposed approach could model the export behavior reasonably well compared to a direct neural network approach.