ABSTRACT
The global foreign exchange market is the largest market in the world with its unparalleled volume of transactions. To be more precise, the transaction volume in the global foreign exchange market was recorded at $6.6 trillion a day on average by the Bank for International Settlements in 2019. In 1983, Richard Meese and Kenneth Rogoff demonstrated the inability of the most prominent structural and time series models of the early 1980s, used to explain exchange rates, as useful predictive models. Predicting the future exchange rates with acceptable accuracy would make the lives of investors and policymakers so much easier–if only they could. Moreover, predicting the direction of exchange rates is important information for many agents in financial markets. However, there is a good chance that we can improve our prediction accuracy radically if we focus on making predictions on the possible direction of the future exchange rates rather than making point estimations.
