A stock market trading system based on foreign and domestic information

Abstract

This paper investigates whether a particular magnitude and direction of inter-regional return signal transmission dominates the performance of domestic trading in American, European and Australasian stock markets. A trading system design, based on fuzzy logic rules, combines direct and indirect channels of foreign information transmission, modelled by stochastic parameter regressions, with domestic momentum information to generate stock market trading signals. Filters that control for magnitude and direction of trading signals are then used to investigate incremental impact on economic performance of the proposed investment system. The results indicate that at reasonable levels of transaction costs very profitable trades that are fewer in number do not increase investment performance as much as trades based on foreign information of a specific low-to-medium daily return magnitude of 0.5% to 0.75%. These information-based strategies are profitable on risk-adjusted bases and relative to a market, but performance declines considerably when tradable instruments are used.