Showing papers on "Foreign exchange market published in 2017"

Deep networks for predicting direction of change in foreign exchange rates

Abstract: Summary Trillions of dollars are traded daily on the foreign exchange (forex) market, making it the largest financial market in the world. Accurate forecasting of forex rates is a necessary element in any effective hedging or speculation strategy in the forex market. Time series models and shallow neural networks provide acceptable point estimates for future rates but are poor at predicting the direction of change and, hence, are not very useful for supporting profitable trading strategies. Machine learning classifiers trained on input features crafted based on domain knowledge produce marginally better results. The recent success of deep networks is partially attributable to their ability to learn abstract features from raw data. This motivates us to investigate the ability of deep convolution neural networks to predict the direction of change in forex rates. Exchange rates for the currency pairs EUR/USD, GBP/USD and JPY/USD are used in experiments. Results demonstrate that trained deep networks achieve satisfactory out-of-sample prediction accuracy.

A stacked generalization system for automated FOREX portfolio trading

Abstract: Multiple FOREX time series forecasting is a hot research topic in the literature of portfolio trading. To this end, a large variety of machine learning algorithms have been examined. However, it is now widely understood that, in real-world trading settings, no single machine learning model can consistently outperform the alternatives. In this work, we examine the efficacy and the feasibility of developing a stacked generalization system, intelligently combining the predictions of diverse machine learning models. Our approach establishes a novel inferential framework that comprises the following levels of data processing: (i) We model the dependence patterns between major currency pairs via a diverse set of commonly used machine learning algorithms, namely support vector machines (SVMs), random forests (RFs), Bayesian autoregressive trees (BART), dense-layer neural networks (NNs), and naive Bayes (NB) classifiers. (ii) We generate implied signals of exchange rate fluctuation, based on the output of these models, as well as appropriate side information obtained by analyzing the correlations across currency pairs in our training datasets. (iii) We finally combine these implied signals into an aggregate predictive waveform, by leveraging majority voting, genetic algorithm optimization, and regression weighting techniques. We thoroughly test our framework in real-world trading scenarios; we show that our system leads to significantly better trading performance than the considered benchmarks. Thus, it represents an attractive solution for financial firms and corporations that perform foreign exchange portfolio management and daily trading. Our system can be used as an integrated part in international commercial trade activities or in a quantitative investing framework for algorithmic trading and carry-trade speculation.

Foreign Exchange Rates Forecasting with Convolutional Neural Network

Abstract: In this paper, we introduce a model based on Convolutional Neural Network for forecasting foreign exchange rates. Additionally, a method of transforming exchange rates data from 1D structure to 2D structure is proposed. The transaction of the foreign exchange market has periodic characteristics, however, due to the technical limitations, these characteristics cannot be utilized by existing time series forecasting models. In this paper, we propose a model which can process 2D structure exchange rates data and put these characteristics to good use. Exchange rates Euro against US dollar, US dollar against Japanese yen and British Pound Sterling against US dollar are researched in this paper. Our experimental results show that, when compared with Artificial Neural Network, Support Vector Regression and Gated Recurrent Unit, the proposed model can effectively improve the accuracy of long-term forecasting.

Testing for speculative bubbles using spot and forward prices

Abstract: The probabilistic structure of periodically collapsing bubbles creates a gap between future spot and forward (or futures) asset prices in small samples. By exploiting this fact, we use two econometric methods, namely, the recursive unit root method of Phillips, Shi, and Yu (2015a,b) and the rolling regression method of Fama (1984), for detecting bubbles. Both methods do not rely on a particular model of asset price determination, they are robust to an explosive root in the process for market fundamentals, and are accompanied by a date-stamping strategy. By applying these methods to the German mark-US dollar and British pound-US dollar exchange rates, we provide evidence in favor of speculative bubbles in the foreign exchange market during the interwar German hyperinflation, but not during the recent floating-rate period. A further application to the S&P 500 index supports the existence of speculative bubbles in the US equity market.

A strength-biased prediction model for forecasting exchange rates using support vector machines and genetic algorithms

Abstract: This paper addresses problem of predicting direction and magnitude of movement of currency pairs in the foreign exchange market. The study uses Support Vector Machine with a novel approach for input data and trading strategy. The input data contain technical indicators generated from currency price data (i.e., open, high, low and close prices) and representation of these technical indicators as trend deterministic signals. The input data are also dynamically adapted to each trading day with genetic algorithm. The study incorporates a currency strength-biased trading strategy which selects the best pair to trade from the available set of currencies and is an improvement over the previous work. The accuracy of the prediction models are tested across several different sets of technical indicators and currency pair sets, spanning 5 years of historical data from 2010 to 2015. The experimental results suggest that using trend deterministic technical indicator signals mixed with raw data improves overall performance and dynamically adapting the input data to each trading period results in increased profits. Results also show that using a strength-biased trading strategy among a set of currency pair increases the overall prediction accuracy and profits of the models.

Causal relationship between the global foreign exchange market based on complex networks and entropy theory

Abstract: The foreign exchange (FX) market is a typical complex dynamic system under the background of exchange rate marketization reform and is an important part of the financial market. This study aims to generate an international FX network based on complex network theory. This study employs the mutual information method to judge the nonlinear characteristics of 54 major currencies in international FX markets. Through this method, we find that the FX network possesses a small average path length and a large clustering coefficient under different thresholds and that it exhibits small-world characteristics as a whole. Results show that the relationship between FX rates is close. Volatility can quickly transfer in the whole market, and the FX volatility of influential individual states transfers at a fast pace and a large scale. The period from July 21, 2005 to March 31, 2015 is subdivided into three sub-periods (i.e., before, during, and after the US sub-prime crisis) to analyze the topology evolution of FX markets using the maximum spanning tree approach. Results show that the USD gradually lost its core position, EUR remained a stable center, and the center of the Asian cluster became unstable. Liang's entropy theory is used to analyze the causal relationship between the four large clusters of the world.

Term Structure of Consumption Risk Premia in the Cross Section of Currency Returns

Abstract: I quantify the risk-return relationship in the foreign exchange market in the cross-section and across investment horizons by focusing on the role of multiple sources of US consumption risk. To this end, I estimate a flexible structural model of the joint dynamics of aggregate consumption, inflation, nominal interest rate, and stochastic variance with cross-equation restrictions implied by recursive preferences. I identify the following four structural shocks: inflation, short-run, longrun and variance consumption risks. To measure their relative importance, I compute marginal quantities and prices of risk (marginal Sharpe ratios) in the cross-section of currency baskets for alternative investment horizons. I find that the long-run consumption risk plays a prominent role: it carries an average quarterly Sharpe ratio of 0.28 and contributes to the spread in excess returns between baskets of high and low interest rate currencies across investment horizons from one to five quarters. The short-run consumption risk has an e↵ect on currencies at the horizon of one quarter only, where it explains at least 40% of the corresponding spread in excess returns. The carry trade profitability disappears at horizons longer than four quarters.

How did China’s foreign exchange reform affect the efficiency of foreign exchange market?

Abstract: This study compares the market efficiency of China’s onshore and offshore foreign exchange markets before and after the foreign exchange reform on August 11, 2015. We use the multifractal detrended fluctuation analysis of the onshore and offshore RMB/USD spot exchange rate series as basis. We then find that the onshore foreign exchange market before the reform has the lowest market efficiency, which increased after the reform. The offshore foreign exchange market before the reform has the highest market efficiency, which dropped after the reform. This finding implies the increased efficiency of the onshore foreign exchange market and the loss of efficiency in the offshore foreign exchange market. We also find that the offshore foreign exchange market is more efficient than the onshore market and that the gap shrank after the reform. Changes in intervention of the People’s Bank of China since the reform is a possible explanation for the changes in the efficiency of the foreign exchange market.

Dynamic relationship between Japanese Yen exchange rates and market anxiety: A new perspective based on MF-DCCA

Abstract: This paper investigates the dynamic relationship between Japanese Yen exchange rates and market anxiety during the period from January 5, 1998 to April 18, 2016. A quantitative technique of multifractal detrended cross-correlation analysis (MF-DCCA) is used to explore the multifractal features of the cross-correlations between USD/JPY, AUD/JPY exchange rates and the market anxiety gauge VIX. The investigation shows that the causal relationship between Japanese Yen exchange rates and VIX are bidirectional in general, and the cross-correlations between the two sets of time series are multifractal. Strong evidence suggests that the cross-correlation exponents tend to exhibit different volatility patterns in response to diverse external shocks such as financial distress and widening in interest rate spread, suggesting that the cross-correlated behavior between Japanese Yen exchange rates and VIX are susceptible to economic uncertainties and risks. In addition, the performances of two market anxiety gauges, the VIX and the TED spread, are compared and the sources of multifractality are also traced. Thus, this paper contributes to the literature by shedding light on the unique driving forces of the Yen exchange rate fluctuations in the international foreign exchange market.

Real exchange rate persistence and the excess return puzzle: The case of Switzerland versus the US

Abstract: Summary The PPP puzzle refers to the wide swings of nominal exchange rates around their long-run equilibrium values whereas the excess return puzzle represents the persistent deviation of the domestic-foreign interest rate differential from the expected change in the nominal exchange rate. Using the I(2) cointegrated VAR model, much of the excess return puzzle disappears when an uncertainty premium in the foreign exchange market, proxied by the persistent PPP gap, is introduced. Self-reinforcing feedback mechanisms seem to cause the persistence in the Swiss-US parity conditions. These results support imperfect knowledge based expectations rather than so-called “rational expectations”.

Government Intervention and Arbitrage

Abstract: We model and document the novel notion that direct government intervention in a market may induce violations of the law of one price (LOP) in other, arbitrage-related markets. We show that the introduction of a government pursuing a non-public, partially informative price target in a model of strategic trading and segmented dealership generates equilibrium price differentials among fundamentally identical (or linearly related) assets -- especially when markets are illiquid, LOP violations are small, speculators are heterogeneously informed, or policy uncertainty is high. We find supportive evidence in a sample of ADRs traded in U.S. exchanges and currency interventions by developed and emerging countries between 1980 and 2009.

Central Banks and Macroeconomic Policy Choices: Relaxing the Trilemma

Abstract: Macroeconomic policy choices in open economies are constrained by the trilemma according to which the objectives of exchange rate stability, monetary independence and capital mobility cannot be attained jointly. This paper shows that foreign exchange interventions provide an effective instrument to relax the trilemma. An active reserve policy allows central banks to pursue independent monetary and exchange rate policies when the capital account is liberalised. We use the framework of the portfolio balance model to show that exchange market interventions may substitute for capital controls. Both allow a country to achieve the other two objectives of the trilemma. Our empirical analysis of a large country panel data set covering the period 1970–2010 confirms this theoretical insight: the weighted sum of the three trilemma objectives increases in the degree of foreign exchange market intervention. The capacity to relax the trilemma constraint has increased over time and has been most effective in emerging markets.

Jumps, Cojumps, and Efficiency in the Spot Foreign Exchange Market

Abstract: This paper identifies intraday jumps and cojumps in exchange rates controlling for volatility patterns and relates these events to pre-scheduled macroeconomic news and market state. Event study results show that preceding jump and cojump events, exchange rate quote volume, illiquidity, signed order flow, and informed trade are at heightened levels revealing that jump events are consistent with rational dealer quoting behavior. Following jump and cojump events, quote volume and return variance remain at heightened levels while illiquidity, informed trade, and signed order flow remain at depressed levels providing evidence that order flow following jump events is largely uninformed liquidity provision.

Dynamic Currency Linkages and Their Determinants: An Empirical Study for East Asian Economic Community Region

Abstract: In this article, Copula GARCH models have been employed to study the inter-temporal process of currency market co-movements between ASEAN+6 countries (referred to in this study as East Asian Econom...