Deep networks for predicting direction of change in foreign exchange rates

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.     

Heuristic learning in intraday trading under uncertainty

Until recently economists focused on structural models that were constrained by a lack of high-frequency data and theoretical deficiencies. Little academic research has been invested in actually trying to build successful real-time trading models for the high-frequency foreign exchange market, which is characterized by inherent complexity and heterogeneity. The present work opens new directions for inference on market efficiency in an attempt to account for the use of technical analysis by practitioners over many years now. This paper presents a heuristic model that efficiently emulates the dynamic learning of intraday traders. The proposed setup incorporates agent beliefs, preferences and expectations while it integrates the calibration of technical rules by means of adaptive training. The study focuses on EUR/USD which is the most liquid and widely traded currency pair. The data consist of a very large tick-by-tick sample of bid and ask prices covering many trading periods to enhance robustness in the results. The efficiency of a technical trading strategy based on the proposed model is investigated in terms of directional predictability. The heuristic learning system is compared against many non-linear models, a random walk and a buy & hold strategy. Based on statistical testing it is shown that, with the inclusion of transaction costs, the profitability of the new model is consistently superior. These findings provide evidence of technical predictability under incomplete information and can be justified by invoking the existence of heterogeneity caused by many factors affecting market microstructure. Overall, the results suggest that the proposed model can be used to improve upon traditional technical analysis approaches.     

TESTS OF RANDOM WALK AND MARKET EFFICIENCY FOR LATIN AMERICAN EMERGING EQUITY MARKETS

Variance-ratio methodology is used to test the hypothesis that Latin American emerging equity market prices follow a random walk. The data are monthly index prices in local currency from December 1975 to March 1991 for Argentina, Brazil, Chile, and Mexico. The variance-ratio tests reject the random walk hypothesis. However, runs tests indicate that Latin American equity markets are weak-form efficient. These empirical findings suggest that domestic investors might not be able to develop trading strategies that would allow them to earn excess returns.     

Do currency exchange rates impact gold prices? New evidence from the ongoing COVID-19 period

We apply the nonlinear autoregressive distributed lag method to examine the relationships between seven leading currency exchange rates and gold prices using daily data from January 2017 to April 2021. The results reveal that in the short term, while negative United States dollar (USD) to United Kingdom pound, negative USD to Canadian dollar, negative USD to Japanese yen, negative USD to Danish krone, and positive USD to euro exchange rates increase gold prices, a lagged positive USD to euro and lagged positive USD to Danish krone exchange rates decrease gold prices. A test of the pre-pandemic normal period reveals that the uneven and unpredictable impacts of six exchange rates on gold prices are particularly due to COVID-19. We find efficiency in the gold market, in line with the market efficiency hypothesis and random walk theory. Our findings indicate that gold acts as a safe-haven asset for investors during COVID-19.     

Performance of Currency Trading Strategies in Developed and Emerging Markets: Some Striking Differences

Expanding the currency investment universe makes a lot of sense from a diversification point of view. Nevertheless, 60% of the total foreign exchange turnover is still only traded in three currency pairs (USD/EUR, USD/JPY and USD/GBP). The share of trading in local currencies in emerging markets is only around 5%. This can be explained by the fact that some currency managers fear investing in emerging market currencies. Many believe that political risk is the most dominant driver in these markets and that traditional investment rules do not work. In this paper, I apply four technical trading strategies for the developed market currencies and for the most traded emerging market currencies. The empirical results show some striking differences. They suggest that trend-following rules work better for emerging market currencies, while carry trading strategies perform better across developed market currencies. Nevertheless, it seems that conventional techniques could be successfully applied to both developed and emerging market currencies. I conclude that currency managers should not be afraid to diversify into emerging market currencies. They should, however, adjust their trading style accordingly.     

国际金融危机与美元国际储备货币地位的变化

文章认为,国际金融危机使美元面临重大挑战。文章分析了危机中美元仍维持主要储备货币地位的原因,主要包括大量黄金储备的支撑作用、美国金融市场对全球资金的吸引、主要竞争对手未成熟完善、回复（改良的）金本位并不可行等。最后,文章展望了美国货币政策走向和美元汇率行情,以及相关货币与美元的关系。     

Stock price prediction using DEEP learning algorithm and its comparison with machine learning algorithms

Security indices are the main tools for evaluation of the status of financial markets. Moreover, a main part of the economy of any country is constituted of investment in stock markets. Therefore, investors could maximize the return of investment if it becomes possible to predict the future trend of stock market with appropriate methods. The nonlinearity and nonstationarity of financial series make their prediction complicated. This study seeks to evaluate the prediction power of machine‐learning models in a stock market. The data used in this study include the daily close price data of iShares MSCI United Kingdom exchange‐traded fund from January 2015 to June 2018. The prediction process is done through four models of machine‐learning algorithms. The results indicate that the deep learning method is better in prediction than the other methods, and the support vector regression method is in the next rank with respect to neural network and random forest methods with less error.     

Do corporations learn from mispricing? Evidence from takeovers and corporate performance

In this article we form the simple prediction that mispricing encourages traders to collect costly information that guides managerial decisions at corporate level. Our findings support this prediction based on evidence derived from both the US market for corporate control and the overall variation in aggregate corporate profits. The trading activity in response to the temporary mispricing of the merging companies provides useful information that leads to the design of high-synergy deals. Such synergies are reflected in an increase in the announcement period acquirer abnormal returns and are not reversed in the long-run. At the market-wide level, our results suggest that the growth in the overall stock trading volume in response to market mispricing is associated with high future corporate profit growth. Overall, after controlling for several economic and financial conditions, the temporary mispricing in a developed and generally efficient stock market stimulates informative trading, ultimately leading to value- and performance-enhancing corporate decisions.     

中国银行间市场开创卢布交易业务完善市场功能

1994年人民币汇率形成机制改革以来,中国银行间外汇市场挂牌了美元、欧元、日元、英镑和港币等五种国际储备货币。本轮国际金融危机以来,主要货币汇率波动加大,微观主体出于节约汇兑成本的需要,对人民币与新兴市场货币兑换交易的需求不断上升。为满足经济主体的需求,中国人民银行积极探索在银行间外汇市场挂牌人民币对新兴市场货币交易。2010年11月22日,中国银行间外汇市场挂牌人民币对卢布交易。挂牌以来,中国银行间外汇市场人民币对新兴市场货币交易健康发展,报价日益活跃,成交快速增长。截至2011年9月末,银行间外汇市场人民币对卢布成交53.10亿元人民币,2011年下半年以来的交易量也已超过了人民币对英镑的交易量。在我国银行间市场挂牌人民币对卢布交易一周年之际,本刊特推出四家人民币对卢布做市商相关经验与感想的专题文章,供市场参考。     

The role of attribute selection in Deep ANNs learning framework for high‐frequency financial trading

In financial trading, technical and quantitative analysis tools are used for the development of decision support systems. Although these traditional tools are useful, new techniques in the field of machine learning have been developed for time‐series forecasting. This paper analyses the role of attribute selection on the development of a simple deep‐learning ANN (D‐ANN) multi‐agent framework to accomplish a profitable trading strategy in the course of a series of trading simulations in the foreign exchange market. The paper evaluates the performance of the D‐ANN multi‐agent framework over different time spans of high‐frequency (HF) intraday asset time‐series data and determines how a set of the framework attributes produces effective forecasting for profitable trading. The paper shows the existence of predictable short‐term price trends in the market time series, and an understanding of the probability of price movements may be useful to HF traders. The results of this paper can be used to further develop financial decision‐support systems and autonomous trading strategies for the financial market.     

Official FX interventions through derivatives

We use high-frequency data to study the effects of currency swap auctions carried out by the Brazilian Central Bank on the USDBRL exchange rate. We find that official currency swap auctions impact the exchange rate in a significant way, even though they do not directly alter the supply of foreign currency in the market. We show that during our sample period auctions of contracts in which the Central Bank took a short position in USD had larger effects than those in which the Central Bank took a long position. The supply of currency swaps to the market provides an alternative for traders that demand foreign currency for financial (speculative or hedging) rather than transactional reasons, and thus affects the demand for foreign currency and its price. This mechanism is likely to be particularly relevant when forecasters extrapolate exchange rate trends at short-term horizons.     

2012年5月银行问市场运行报告

2012年5月,银行间市场整体平稳运行,主要特点是：市场资金面宽松,货币市场利率持续走低;银行间国债收益率曲线整体下移,利率互换成交曲线也出现明显下移;国际市场美元指数飙升,人民币对美元汇率显著走§5,人民币对欧元汇率破八,汇率盘中波动和升贬预期较为稳定;外汇衍生品成交活跃,市场份额进一步上升。     

Random walk theory and the weak-form efficiency of the US art auction prices

We perform variance ratio tests based on non-parametric methods to detect the size of the random walk component of the US art auction prices. The past 134 years of the US art prices exhibit large transitory component (72%) and based on this, the random walk hypothesis does not hold. However, possibly due to sparse data before 1935 or due to institutional changes of the art market after World War II, we detect structural breakpoints and find that the random walk hypothesis and the weak-form efficiency of the US art market cannot be rejected at least for the past 64 years.     

Testing the Random Walk Behavior and Efficiency of the Gulf Stock Markets

Inferences drawn from tests of market efficiency are rendered imprecise in the presence of infrequent trading. As the observed index in thinly traded markets may not represent the true underlying index value, there is a systematic bias toward rejecting the efficient market hypothesis. For the three emerging Gulf markets examined in this paper, correction for infrequent trading significantly alters the results of market efficiency and random walk tests. The Beveridge–Nelson (1981) decomposition of index returns is done to estimate the underlying index.     

Making trading decisions for financial‐engineered derivatives: a novel ensemble of neural networks using information content

Over the last decades, there has been a growing interest in applying artificial intelligence techniques to solve a spectrum of financial problems. A number of studies have shown promising results in using artificial neural networks (ANNs) to guide investment trading. Given the expanding role of ANNs in financial trading, this paper proposes the use of a hybrid neural network, which consists of two independent ANN architectures, and comparatively evaluates its performance against independent ANNs and econometric models in the trading of a financial‐engineered (synthetic) derivative composed of options on foreign exchange futures. We examine the financial profitability and the market timing ability of the competing neural network models and statistically compare their attributes with those based on linear and nonlinear statistical projections. A random walk model and the option pricing method are also included as benchmarks for comparison. Our empirical investigation finds that, for each of the currencies analysed, trading strategies guided by the proposed dual network are financially profitable and yield a more stable stream of investment returns than the other models. Statistical results strengthen the notion that diffusion of information contents and cross‐validation between the independent components within the dual network are able to reduce bias and extreme decision making over the long run. Moreover, the results are robust with respect to different levels of transaction costs. Copyright © 2009 John Wiley & Sons, Ltd.     

Generative Bayesian neural network model for risk-neutral pricing of American index options

Financial models with stochastic volatility or jumps play a critical role as alternative option pricing models for the classical Black–Scholes model, which have the ability to fit different market volatility structures. Recently, machine learning models have elicited considerable attention from researchers because of their improved prediction accuracy in pricing financial derivatives. We propose a generative Bayesian learning model that incorporates a prior reflecting a risk-neutral pricing structure to provide fair prices for the deep ITM and the deep OTM options that are rarely traded. We conduct a comprehensive empirical study to compare classical financial option models with machine learning models in terms of model estimation and prediction using S&P 100 American put options from 2003 to 2012. Results indicate that machine learning models demonstrate better prediction performance than the classical financial option models. Especially, we observe that the generative Bayesian neural network model demonstrates the best overall prediction performance.     

Nonparametric testing of the high-frequency efficiency of the 1997 Asian foreign exchange markets

Sherry’s nonparametric pattern tests for neural information processing are used to ascertain if the Asian foreign exchange (FX) rates followed random walks [Sherry, C.J., 1992. The Mathematics of Technical Analysis: Applying Statistics to Trading Stocks, Options and Futuresm Probus, Chicago]. The stationarity and serial independence of the price changes are tested on minute-by-minute data for nine Asian currencies from 1 January 1997 to 30 December 1997. The efficiency of these FX markets before and after the Asian currency ‘regime discontinuity’ are compared. The Thai baht (THB), Malaysian ringgit (MYR), Indonesian rupiah (IDR) and Singapore dollar (SGD) exhibited non-stationary behavior during the entire year, and gave evidence of a trading regime break, while the Phillipines’ peso (PHP), Taiwan dollar (TWD), Japanese yen (JYP) and German deutschmark (DEM) remained stationary, with the US dollar (USD) as numeraire. However, each half-year regime showed stationarity, indicating stable and nonchaotic trading regimes for all currencies, despite their high volatilities, except for the MYR, which exhibited non-stationarity in the second half of 1997. The Thai baht traded nonstationarily in the first half of 1997, but stationarily in the second half. while the TWD reversed that trading pattern. Based on Sherry’s four tests for serial independence, none of the currencies exhibited complete independence. Thus no Asian currency market—including the JYP—exhibited complete efficiency in 1997, in particular when compared with the highly efficient DEM. Remarkably, the PHP remained as efficient as the JYP throughout 1997.     

Evaluating interpretable machine learning predictions for cryptocurrencies

This study explores various machine learning and deep learning applications on financial data modelling, analysis and prediction processes. The main focus is to test the prediction accuracy of cryptocurrency hourly returns and to explore, analyse and showcase the various interpretability features of the ML models. The study considers the six most dominant cryptocurrencies in the market: Bitcoin, Ethereum, Binance Coin, Cardano, Ripple and Litecoin. The experimental settings explore the formation of the corresponding datasets from technical, fundamental and statistical analysis. The paper compares various existing and enhanced algorithms and explains their results, features and limitations. The algorithms include decision trees, random forests and ensemble methods, SVM, neural networks, single and multiple features N-BEATS, ARIMA and Google AutoML. From experimental results, we see that predicting cryptocurrency returns is possible. However, prediction algorithms may not generalise for different assets and markets over long periods. There is no clear winner that satisfies all requirements, and the main choice of algorithm will be tied to the user needs and provided resources.     

Measuring informational efficiency of the European carbon market — A quantitative evaluation of higher order dependence

This paper introduces a new method for measuring nonlinear predictability in financial price changes: the so-called intermittency coefficient, a parameter of the multifractal random walk model by Bacry et al. (2001). As the intermittency coefficient can quantify the degree of nonlinear deviation from a random walk, we employ its estimates from financial data as a proxy for the loss of financial market efficiency. In addition, we propose a new statistical test of the random walk hypothesis. In an empirical application using data from the largest currently existing market for tradable pollution permits, the European Union Emissions Trading Scheme (EU ETS), we show that the degree of efficiency of this market remains largely unchanged over the period of observation 2008–2019. This suggests that the market has reached a mature state: informational efficiency in Phase III remains at a level comparable to Phase II. What is more, the EU ETS is found to be more efficient than the US stock market. This result, surprising as such, is largely attributable to the lower exposure to global economic shocks of the EU ETS.     

Can commodity futures be profitably traded with quantitative market timing strategies?

Quantitative market timing strategies are not consistently profitable when applied to 15 major commodity futures series. We conduct the most comprehensive study of quantitative trading rules in this market setting to date. We consider over 7000 rules, employ two alternative bootstrapping methodologies, account for data-snooping bias, and consider different time periods. We cannot rule out the possibility that trading rules compliment some other trading strategy or that some traders may have success using a specific rule on its own, but we do conclusively show that none of these rules beat the market any more than expected given random data variation.