Forecasting risk in the US Dollar exchange rate under volatility shifts

Recent evidence suggests that volatility shifts (i.e. structural breaks in volatility) in returns increases kurtosis which significantly contributes to the observed non-normality in market returns. In this paper, we endogenously detect significant shifts in the volatility of US Dollar exchange rate and incorporate this information to estimate Value-at-Risk (VaR) to forecast large declines in the US Dollar exchange rate. Our out-of-sample performance results indicate that a GARCH model with volatility shifts produces the most accurate VaR forecast relative to several benchmark methods. Our contribution is important as changes in US Dollar exchange rate have a substantial impact on the global economy and financial markets.     

Causality and volatility patterns between gold prices and exchange rates

This paper provides a new perspective on the link between gold prices and exchange rates. Based on gold prices denominated in five different currencies and the related bilateral exchange rates, we put causalities and short-run volatility transmission under closer scrutiny. We provide evidence that the identification of a strong hedge function of gold requires an explicit modeling of the volatility component. For all currencies, exchange rate depreciations initially have a negative impact on the gold price after one day which turns out to be positive after two days in most of the cases. Contrary to previous studies, our results point to a specific role of the dollar in the context of gold-exchange rate relationships: volatility of dollar exchange rates more frequently results in strong hedging functions of gold prices. Furthermore, the gold price denominated in the US dollar tends to increase after a depreciation of the dollar.     

Forecasting exchange rates with elliptically symmetric principal components

We extract elliptically symmetric principal components from a panel of 17 OECD exchange rates and use the deviations from the components to forecast future exchange rate movements, following the method in Engel et al. (2015). Instead of using standard factor models, we apply elliptically symmetric principal component analysis (ESPCA), introduced by Solat and Spanos (2018), which captures both contemporaneous and temporal co-variation among the exchange rates. We find that ESPCA is more accurate than forecasts generated by existing standard methods and the random walk model, with or without including macroeconomic fundamentals.     

Testing the forward volatility unbiasedness hypothesis in exchange rates under long-range dependence

This paper analyses the unbiasedness hypothesis between spot and forward volatility, using both the actual and the continuous path of realised volatility, and focusing on long-memory properties. For this purpose, we use daily realised volatility with jumps for the USD/EUR exchange rate negotiated in the FX market and employ fractional integration and cointegration techniques. Both series have long-range dependence, and so does the error correction term of their long-run relationship. Hence, deviations from equilibrium are highly persistent, and the effects of shocks affecting the long-run relationship dissipate very slowly. While for long-term contracts, there is some empirical evidence that the forward volatility unbiasedness hypothesis does not hold – and, thus, that forward implied volatility is a systematically downward-biased predictor of future spot volatility – for short-term contracts, the evidence is mixed.     

Forecasting cryptocurrency volatility

This paper studies the behavior of cryptocurrencies’ financial time series, of which Bitcoin is the most prominent example. The dynamics of these series are quite complex, displaying extreme observations, asymmetries, and several nonlinear characteristics that are difficult to model and forecast. We develop a new dynamic model that is able to account for long memory and asymmetries in the volatility process, as well as for the presence of time-varying skewness and kurtosis. The empirical application, carried out on 606 cryptocurrencies, indicates that a robust filter for the volatility of cryptocurrencies is strongly required. Forecasting results show that the inclusion of time-varying skewness systematically improves volatility, density, and quantile predictions at different horizons.     

Forecasting volatility with time-varying leverage and volatility of volatility effects

Predicting volatility is of primary importance for business applications in risk management, asset allocation, and the pricing of derivative instruments. This paper proposes a measurement model that considers the possibly time-varying interaction of realized volatility and asset returns according to a bivariate model to capture its major characteristics: (i) the long-term memory of the volatility process, (ii) the heavy-tailedness of the distribution of returns, and (iii) the negative dependence of volatility and daily market returns. We assess the relevance of the effects of “the volatility of volatility” and time-varying “leverage” to the out-of-sample forecasting performance of the model, and evaluate the density of forecasts of market volatility. Empirical results show that our specification can outperform the benchmark HAR–GARCH model in terms of both point and density forecasts.     

Forecasting foreign exchange rates: an expert judgment approach

Studies have indicated that forecasts by market experts can be more accurate than time series forecasts. This article describes a process for structuring an expert foreign exchange forecast using Saaty's Analytic Hierarchy Process (AHP). The specific example developed is a forecast of the yen/dollar spot exchange rate from the standpoint of a company considering the desirability of arranging for forward exchange cover.     

Forecasting exchange rates using feedforward and recurrent neural networks

In this paper we investigate the out-of-sample forecasting ability of feedforward and recurrent neural networks based on empirical foreign exchange rate data. A two-step procedure is proposed to construct suitable networks, in which networks are selected based on the predictive stochastic complexity (PSC) criterion, and the selected networks are estimated using both recursive Newton algorithms and the method of nonlinear least squares. Our results show that PSC is a sensible criterion for selecting networks and for certain exchange rate series, some selected network models have significant market timing ability and/or significantly lower out-of-sample mean squared prediction error relative to the random walk model.     

Forecasting crude oil price volatility

We use high-frequency intra-day realized volatility data to evaluate the relative forecasting performances of various models that are used commonly for forecasting the volatility of crude oil daily spot returns at multiple horizons. These models include the RiskMetrics, GARCH, asymmetric GARCH, fractional integrated GARCH and Markov switching GARCH models. We begin by implementing Carrasco, Hu, and Ploberger’s (2014) test for regime switching in the mean and variance of the GARCH(1, 1), and find overwhelming support for regime switching. We then perform a comprehensive out-of-sample forecasting performance evaluation using a battery of tests. We find that, under the MSE and QLIKE loss functions: (i) models with a Student’s t innovation are favored over those with a normal innovation; (ii) RiskMetrics and GARCH(1, 1) have good predictive accuracies at short forecast horizons, whereas EGARCH(1, 1) yields the most accurate forecasts at medium horizons; and (iii) the Markov switching GARCH shows a superior predictive accuracy at long horizons. These results are established by computing the equal predictive ability test of Diebold and Mariano (1995) and West (1996) and the model confidence set of Hansen, Lunde, and Nason (2011) over the entire evaluation sample. In addition, a comparison of the MSPE ratios computed using a rolling window suggests that the Markov switching GARCH model is better at predicting the volatility during periods of turmoil.     

Jump probability using volatility periodicity filters in US Dollar/Euro exchange rates

The discrete daily and intraday jump probabilities of US dollar/euro returns from February 2010 to February 2018 are analyzed using five-minute returns considering several periodicity filters of volatility. When the max outlying statistics are used with Gumbel distribution with periodicity filters such as weighted standard deviation, shortest half scale, and median absolute deviation, the empirical estimates show that the five-minute US dollar/euro returns have lower daily jump probabilities by 13–28% at common critical levels. To detect intraday jumps using the max outlying Gumbel jump statistics, the five-minute US dollar/euro returns have lower daily jump probabilities by 2–10% when the periodicity filters are included at common critical levels. Therefore, when the periodicity filters of volatility are considered, the five-minute US dollar/euro returns have significantly lower daily and intraday jump probabilities than when the periodicity filters are not considered.     

Forecasting realized volatility of agricultural commodities

We forecast the realized and median realized volatility of agricultural commodities using variants of the heterogeneous autoregressive (HAR) model. We obtain tick-by-tick data on five widely-traded agricultural commodities (corn, rough rice, soybeans, sugar, and wheat) from the CME/ICE. Real out-of-sample forecasts are produced for between 1 and 66 days ahead. Our in-sample analysis shows that the variants of the HAR model which decompose volatility measures into their continuous path and jump components and incorporate leverage effects offer better fitting in the predictive regressions. However, we demonstrate convincingly that such HAR extensions do not offer any superior predictive ability in their out-of-sample results, since none of these extensions produce significantly better forecasts than the simple HAR model. Our results remain robust even when we evaluate them in a Value-at-Risk framework. Thus, there is no benefit from including more complexity, related to the volatility decomposition or relative transformations of the volatility, in the forecasting models.     

Forecasting multivariate realized stock market volatility

We present a new matrix-logarithm model of the realized covariance matrix of stock returns. The model uses latent factors which are functions of lagged volatility, lagged returns and other forecasting variables. The model has several advantages: it is parsimonious; it does not require imposing parameter restrictions; and, it results in a positive-definite estimated covariance matrix. We apply the model to the covariance matrix of size-sorted stock returns and find that two factors are sufficient to capture most of the dynamics.     

Tests of the martingale hypothesis for foreign currency futures with time-varying volatility

The martingale hypothesis for daily and weekly rates of change of futures prices for five currencies is tested in this paper. With daily data, we find some evidence against the null hypothesis for each currency. Although institutionally imposed limits on daily price changes were binding fairly often in the earlier years of the sample, the results are not substantially different when data affected by limit moves are removed. Trading day effects in foreign currency futures and spot prices introduce complicated day of the week patterns in futures price. For this reason, we retest the martingale hypothesis with weekly data and reject the null hypothesis for only one currency. For this currency, one interpretation of the evidence is that a time-varying risk premium exists.     

Pricing currency options with scheduled and unscheduled announcement effects on volatility

It is well documented that exchange rate volatility is time-varying and that it can be affected by scheduled events such as money supply announcements and unscheduled ones such as spot market interventions and interest rate changes. This study provides a European event model (E model) for currency call options that explicitly addresses the volatility effects of these two classes of events. Managers who are concerned with hedging in an environment of changing volatility may find the E model useful. The E and modified Black-Scholes (MBS) models have similar average errors in predicting option price changes across event windows and do better than a naive no-change prediction. The E model tends to reduce the underpricing of convex, short-term out-of-the-money options and the mispricing of most classes of convex options.     

Forecasting the Value-at-Risk of REITs using realized volatility jump models

This paper examines jump risk in the time series of Real Estate Investment Trusts (REITs). Using high-frequency index-level and firm-level data, the econometric model in this paper integrates jumps into the volatility forecast by estimating jump augmented Heterogeneous Autoregressive (HAR) models of realized volatility. To assess the information value of these specifications, their forecasting accuracies for generating one-step ahead daily Value-at-Risk are also compared with other VaR specifications, including those generated from historical returns, bootstrap technique, and severity loss distribution.     

Capital control and exchange rate volatility

The study offers one conceptual and theoretical framework for evaluating the economic effects of a trading tax on foreign exchange transactions. Taxes and the price stickiness mechanism are taken into account in the model. When prices are flexible, full monetary neutrality can be obtained even in the short-term. Intuitively, taxes on foreign exchange transactions discourage speculation by rising currency trading costs, and, thus, increase the stability of the exchange rate. Finally, the results show that not only the exchange rate but consumption, investment and employment will become less volatile by imposing trading taxes on foreign exchange transactions.     

Asymmetric volatility spillover in the Tokyo stock exchange

This paper examines volatility transfers between size-based stock indexes from the Tokyo Stock Exchange. We use a bivariate EGARCH model to test for volatility spillover effects between large- and small-cap stock indexes. We find an asymmetric volatility spillover from large-cap stock returns to small-cap returns, but not vice versa. We also find a small-firm January effect, but not a June seasonality, in either large-and small-cap stock returns. Instead, we find that the conditional correlation between large- and small-cap indexes is time-varying, showing a tendency to increase during the month of June.(JEL G12, G15)     

Forecasting volatility with component conditional autoregressive range model

In this paper, we propose a component conditional autoregressive range (CCARR) model for forecasting volatility. The proposed CCARR model assumes that the price range comprises both a long-run (trend) component and a short-run (transitory) component, which has the capacity to capture the long memory property of volatility. The model is intuitive and convenient to implement by using the maximum likelihood estimation method. Empirical analysis using six stock market indices highlights the value of incorporating a second component into range (volatility) modelling and forecasting. In particular, we find that the proposed CCARR model fits the data better than the CARR model, and that it generates more accurate out-of-sample volatility forecasts and contains more information content about the true volatility than the popular GARCH, component GARCH and CARR models.     

Analysis of a network structure of the foreign currency exchange market

We analyse structure of the world foreign currency exchange (FX) market viewed as a network of interacting currencies. We analyse daily time series of FX data for a set of 63 currencies, including gold, silver and platinum. We group together all the exchange rates with a common base currency and study each group separately. By applying the methods of filtered correlation matrix we identify clusters of closely related currencies. The clusters are formed typically according to the economical and geographical factors. We also study topology of weighted minimal spanning trees for different network representations (i.e., for different base currencies) and find that in a majority of representations the network has a hierarchical scale-free structure. In addition, we analyse the temporal evolution of the network and detect that its structure is not stable over time. A medium-term trend can be identified which affects the USD node by decreasing its centrality. Our analysis shows also an increasing role of euro in the world’s currency market.     

News will tell: Forecasting foreign exchange rates based on news story events in the economy calendar

The paper proposes a novel approach to predict intraday directional-movements of currency-pairs in the foreign exchange market based on news story events in the economy calendar. Prior work on using textual data for forecasting foreign exchange market developments does not consider economy calendar events. We consider a rich set of text analytics methods to extract information from news story events and propose a novel sentiment dictionary for the foreign exchange market. The paper shows how news events and corresponding news stories provide valuable information to increase forecast accuracy and inform trading decisions. More specifically, using textual data together with technical indicators as inputs to different machine learning models reveals that the accuracy of market predictions shortly after the release of news is substantially higher than in other periods, which suggests the feasibility of news-based trading. Furthermore, empirical results identify a combination of a gradient boosting algorithm, our new sentiment dictionary, and text-features based-on term frequency weighting to offer the most accurate forecasts. These findings are valuable for traders, risk managers and other consumers of foreign exchange market forecasts and offer guidance how to design accurate prediction systems.