Deep learning has substantially advanced the state-of-the-art in computer vision, natural language processing and other elds. The paper examines the potential of contemporary recurrent deep learning architectures for nancial time series forecasting. Considering the foreign exchange market as...

Deep learning has substantially advanced the state of the art in computer vision, natural language processing, and other fields. The paper examines the potential of deep learning for exchange rate forecasting. We systematically compare long short- term memory networks and gated recurrent units...

Pegging the renminbi (RMB) to the US dollar since 1994 has characterised China’s exchange rate policy, under either a fixed peg or appreciating crawling peg. The current policy, announced in June 2010, of 'floating with reference to a basket' has now in April 2015 made the RMB 19 per cent...

The markets for foreign exchange, energy and residential housing have all been strongly affected by the deregulation and expansion of the financial sector. As a result, they have begun to follow the logic of asset markets. This was especially marked in the case of the foreign exchange market...

This study reexamines the evidence for the Balassa-Samuelson effect for the 1985-2007 period. Cointegrating relationships between the real exchange rate and productivity, real price of oil and government spending are estimated using the Johansen and Stock-Watson procedures. The findings show...