Search

This paper uses data sampled at hourly and daily frequencies to predict Bitcoin returns. We consider various advanced non-linear models based on a multitude of popular technical indicators that represent market trend, momentum, volume, and sentiment. We run a robust empirical exercise to observe the impact of forecast horizon, model type, time period, and the choice of inputs (predictors) on the forecast performance of the competing models. We find that Bitcoin prices are weakly efficient at the hourly frequency. In contrast, technical analysis combined with non-linear forecasting models becomes statistically significantly dominant relative to the random walk model on a daily horizon. Our comparative analysis identifies the random forest model as the most accurate at predicting Bitcoin. The estimated measures of the relative importance of predictors reveal that the nature of investing in the Bitcoin market evolved from trend-following to excessive momentum and sentiment in the most recent time period.

This paper studies volatility cascades across multiple trading horizons in cryptocurrency markets. Using one-minute data on Bitcoin, Ethereum and Ripple against the US dollar, we implement the wavelet Hidden Markov Tree model. This model allows us to estimate the transition probability of high or low volatility at one time scale (horizon) propagating to high or low volatility at the next time scale. We find that when moving from long to short horizons, volatility cascades tend to be symmetric: low volatility at long horizons is likely to be followed by low volatility at short horizons, and high volatility is likely to be followed by high volatility. In contrast, when moving from short to long horizons, volatility cascades are strongly asymmetric: high volatility at short horizons is now likely to be followed by low volatility at long horizons. These results are robust across time periods and cryptocurrencies.

This article explores the profitability of technical trading rules around the COVID-19 pandemic market meltdown for the S&P 500 index, Bitcoin, Comex gold spot, crude oil WTI, and the VIX. Trading rule profits are estimated from January to May 2020, including three sub-periods, on a high-frequency data set. The results reveal that the trading rules can beat the buy-and-hold trading strategy. However, only the Bollinger Bands and trading range break-out rules become profitable after transaction costs during the market crash. Moreover, it is found that composite trading signals effectively improve the profitability of technical analysis around the COVID-19 market crash.

This paper addresses the interpretability problem of non-parametric option pricing models by using the explainable artificial intelligence (XAI) approach. We study call options written on the SP 500 stock market index across three market regimes: pre-COVID-19, COVID-19 market crash, and post-COVID-19 recovery. Our comparative option pricing exercise demonstrates the superiority of the random forest and extreme gradient boosting models for each market regime. We also show that the model's pricing accuracy has worsened from the pre-COVID-19 to the recovery period. Moneyness was the most important price determinants across the market regimes, while the implied volatility and time-to-maturity inputs contributed intermittently to a lesser extent. During the COVID-19 crash, open interest gained more economic importance due to the increased behavioral tendencies of traders consistent with market distress.

This paper explores price spillover effects around the COVID-19 pandemic market meltdown between the S&amp, P 500 index, five other financial markets, and the VIX. Frequency domain causalities are estimated for the January–May 2020 time period on a high-frequency data set at five-minute intervals. The results reveal that price movements in the S&amp, P 500 generally caused price movements in other financial markets before the market meltdown, however, a large number of bi-directional causalities emerged during the market meltdown. During the market recovery, S&amp, P 500 price movements were more likely to be caused by other financial markets’ price movements. The VIX, exchange rate, and gold returns had the most prominent influence on the S&amp, P 500 returns in the market recovery.

This paper analyzes the impact of economic freedom along with traditional economic factors on economic growth for a panel of European countries. The growth of the gross domestic product was observed over a twenty-year time period on a sample of 43 developing and developed countries. Based on a robust dynamic panel setting, we conclude that increases in economic freedom as expressed by the Index of Economic Freedom/Heritage Foundation (but not its levels) are related to economic growth. The EU membership status either had no effect or it curbed the effect of the economic freedom on growth. We also find that the subprime economic crisis of 2008&ndash, 2009 exerted a negative impact on the growth of European economies.

International audience; We develop a new framework to characterize the dynamics of triangular (three-point) arbitrage in electronic foreign exchange markets. To examine the properties of arbitrage, we propose a wavelet-based regression approach that is robust to estimation errors, measurement bias and persistence. Relying on this wavelet-based (denoising) inference, we consider various liquidity and market risk indicators to predict arbitrage in a unique ultra-high-frequency exchange rate data set. We find strong empirical evidence that limit order book, realized volatility and cross-correlations help forecast triangular arbitrage profits. The estimates are statistically significant and relevant for investors such that on average 80−100 arbitrage opportunities exist with a short duration (100−500 ms) on a daily basis. Our analysis also reveals that triangular arbitrage opportunities are counter-cyclical at ultra-high-frequency levels: arbitrage returns tend to increase (decrease) in periods when volatility risk and correlations are relatively low (high). We show that liquidity-driven microstructure measures, however, appear to be more powerful in exploiting arbitrage profits when compared to market-driven factors.

International audience; This paper introduces a new empirical framework to identify the regimes of jump‐type tail risk over multiple trading horizons. Our approach combines the hidden Markov regime‐switching model with realized jumps, which allows us to examine the tail risk exposure of investors at different investment scales. Applying our method to data on bonds, stocks, and currencies, we find evidence that market risk linked to jumps exhibits time‐varying regime shifts and horizon‐dependence. We show that high‐frequency trading does not contribute to market instability, as measured by jump risk. The European bond market appears to be more vulnerable to downside (left‐tail) jump risk, relative to the U.S. Treasury bond market. Market jump fear embedded in the VIX exhibits vertical clustering where both risk regimes at low frequencies remain unchanged at higher frequencies. These results suggest that the premium for jump risk not only depends on stress periods, but also on the frequency at which investors trade financial assets.

This article investigates a trading strategy that relies on private information in an electronic spot foreign exchange market. In a structural microstructure model extended for high-frequency data, our analysis links the informational content of trading activity to order size. We find that large currency orders are likely to be placed by informed traders during increased price volatility episodes. In addition, the data suggest that excess kurtosis in exchange rate returns (corresponding to large price-contingent trades) is significantly lower than that in small trades.

This paper concentrates on quantifying the behavioral aspects of systemic risk by using a novel approach based on entropy. More specifically, we study aggregate market expectations and the predictability of systemic risk before and during the financial crisis in 2008. Two underlying signals for estimating entropic risk measures are considered: (i) skewness premium of deepest out-of-the-money options; and (ii) implied volatility ratio in regard to deepest out-of-the-money options. The findings confirm the predictive and contemporaneous usefulness of our entropy setting in market risk management. The degree of predictability is closely linked to both the type of entropy and the nature of the underlying signal. Copyright © 2016 John Wiley & Sons, Ltd.

This paper builds a novel multi-criteria, non-parametric classification framework in order to improve the accuracy of pricing European options. The proposed approach is based on classifying financial options according to their implied volatility, time to maturity and moneyness. Using a recent data set for the daily S&P 500 index call options, the multi-criteria modular neural network model demonstrates its superior out-of-sample pricing performance relative to competing parametric and non-parametric models. By observing the model’s pricing errors across various option types, the analysis provides additional insights into pricing biases and stresses the importance of selecting appropriate classification criteria.

This paper provides a comparative analysis of stock market dynamics of the 1987 and 2008 financial crises and discusses the extent to which risk management measures based on entropy can be successful in predicting aggregate market expectations. We find that the Tsallis entropy is more appropriate for the short and sudden market crash of 1987, while the approximate entropy is the dominant predictor of the prolonged, fundamental crisis of 2008. We conclude by suggesting the use of entropy as a market sentiment indicator in technical analysis.

We develop a new framework to characterize the dynamics of triangular (three-point) arbitrage in electronic foreign exchange markets. To examine the properties of arbitrage, we propose a wavelet-based regression approach that is robust to estimation errors, measurement bias and persistence. Relying on this wavelet-based (denoising) inference, we consider various liquidity and market risk indicators to predict arbitrage in a unique ultra-high-frequency exchange rate data set. We find strong empirical evidence that limit order book, realized volatility and cross-correlations help forecast triangular arbitrage profits. The estimates are statistically significant and relevant for investors such that on average 80−100 arbitrage opportunities exist with a short duration (100−500 milliseconds) on a daily basis. Our analysis also reveals that triangular arbitrage opportunities are counter-cyclical at ultra-high-frequency levels: arbitrage returns tend to increase (decrease) in periods when volatility risk and correlations are relatively low (high). We show that liquidity-driven microstructure measures, however, appear to be more powerful in exploiting arbitrage profits when compared to market-driven factors.

The areas of overlap between the disciplines of marketing and entrepreneurship are substantial and they provide a wide variety of opportunities for multidisciplinary research. This paper lays out multidisciplinary foundations for the formal theoretical and practical treatment of the interaction between marketing, entrepreneurship and profi tability in an organization. The focus of this research is on a company’s success as a function of organizational changes and the level of acceptable risk, measured by its profi tability. The contribution to the literature on the relationship between entrepreneurship and marketing is refl ected in a new approach that relies on the multi-scale (i.e., frequency-dependent) approach or the so-called “spiral of success”. In addition, this paper highlights the necessity for dynamic abilities and innovative character in an organization. More broadly, it explains an important theoretical paradox that organizations always face high risk, but, in order to survive in business, they need to enter new cycles of entrepreneurial activities (innovation and diversifi cation) that involve even more risk. The novelty of this study lies in its application of the causality tests in the frequency domain for the bivariate system in order to demonstrate the marketing-entrepreneurship paradox. This is, to the authors’ best knowledge, the fi rst paper that uses such a methodology in marketing and entrepreneurship. The paper’s principal hypothesis is tested on a well-diversifi ed company (Amazon.com) where it is shown that marketing drives changes in net income at both medium and long horizons, but not vice-versa. The fi ndings and related discussions can be useful to academics and practitioners, as well as to public policy-makers.

This paper tests the theoretical assumption of the foreign exchange market microstructure that dealers and non-dealer customers interact over discrete trading rounds. An exhaustive frequency-domain analysis reveals that the interaction is limited and mainly due to the instability of financial markets. The principal finding is that the trading activity of dealers is able to predict the customer order flow at low frequencies with wavelengths longer than roughly a week. In all, the evidence shows that non-financial customers are not as passive as some other research has suggested.

Bitcoin is the largest cryptocurrency in the world, but its lack of quantitative qualities makes fundamental analysis of its intrinsic value difficult. As an alternative valuation and forecasting method we propose a non-parametric model based on technical analysis. Using simple technical indicators, we produce point and density forecasts of Bitcoin returns with a feedforward neural network. We run several models over the full period of April 2011–March 2018, and four subsamples, and we find that backpropagation neural networks dominate various competing models in terms of their forecast accuracy. We conclude that the dynamics of Bitcoin returns is characterized by predictive local non-linear trends that reflect the speculative nature of cryptocurrency trading.

We study the risk of informed trading in an electronic foreign exchange market and test whether informed trading is driven by marketwide private information. Our framework is based on a structural microstructure trade model that measures the market makers' beliefs directly. Evidence of high concentration of informed trades is found to be inversely related to the overall 24-hour trading activity, i.e., early morning and late afternoon GMT rounds of trading involve the highest risk of informed trading. We structurally identify that the trades due to region-specific private information are dominant and explain between 5 and 25% of the variation in currency returns. In contrast, marketwide private information explains only about 1–5% of the variation in returns.

From the market microstructure perspective, technical analysis can be profitable when informed traders make systematic mistakes or when uninformed traders have predictable impacts on price. However, chartists face a considerable degree of trading uncertainty because technical indicators such as moving averages are essentially imperfect filters with a nonzero phase shift . Consequently, technical trading may result in erroneous trading recommendations and substantial losses. This paper presents an uncertainty reduction approach based on fuzzy logic that addresses two problems related to the uncertainty embedded in technical trading strategies: market timing and order size. The results of our high-frequency exercises show that ‘fuzzy technical indicators’ dominate standard moving average technical indicators and filter rules for the Euro-US dollar (EUR-USD) exchange rates, especially on high-volatility days.

Using a data set from five regional stock exchanges (Serbia, Croatia, Slovenia, Hungary and Germany), this paper presents a frequency domain analysis of a causal relationship between the returns on the CROBEX, SBITOP, CETOP and DAX indices, and the return on the major Serbian stock exchange index, BELEX 15. We find evidence of a somewhat dominant effect of the CROBEX and CETOP stock indices on the BELEX 15 stock index across a range of frequencies. The results also indicate that the BELEX 15 index and the SBITOP index interact in a bi-directional causal fashion. Finally, the DAX index movements consistently drive the BELEX 15 index returns for cycle lengths between 3 and 11 days without any feedback effect.

Using a unique data set from the Bank of Canada, this paper presents the frequency domain analysis of a causal relationship between the Canada/US dollar exchange rate movements and currency order flows. The evidence shows that the existence as well as the direction of causality depends on the customer type, frequency, and time period.

This paper proposes a wavelet (spectral) approach to estimate the parameters of a linear regression model where the regressand and the regressors are persistent processes and contain a measurement error. We propose a wavelet filtering approach which does not require instruments and yields unbiased estimates for the intercept and the slope parameters. Our Monte Carlo results also show that the wavelet approach is particularly effective when measurement errors for the regressand and the regressor are serially correlated. With this paper, we hope to bring a fresh perspective and stimulate further theoretical research in this area.

Non-parametric option pricing models, such as artificial neural networks, are often found to outperform their parametric counterparts in empirical option pricing exercises. In this context, non-parametric models are viewed as more flexible and amenable to adaptive learning. However, the main drawback of non-parametric approaches is their lack of stability, which is detrimental to out-of-sample performance. This is the key reason why one may prefer a parsimonious parametric model. This paper proposes a parametric Takagi–Sugeno–Kang (TSK) fuzzy rule-based option pricing model that requires only a small number of rules to describe highly complex non-linear functions. The findings for this data-driven approach indicate that the TSK model presents a robust option pricing tool that is superior to an array of well-known parametric models from the literature. In addition, its predictive performance is consistently no worse than that of a non-parametric feedforward neural network model.

Many traditional signal processing techniques in finance have limited ability to explain trading processes and distributional properties of the actual market prices. This is typically manifested in model misspecification and pricing and forecasting inaccuracy. For instance, the assumption that log stock returns are normally distributed is widely used in modern mathematical finance.

This paper reviews the recent option pricing literature and investigates how clustering and classification can assist option pricing models. Specifically, we consider non-parametric modular neural network (MNN) models to price the S&P-500 European call options. The focus is on decomposing and classifying options data into a number of sub-models across moneyness and maturity ranges that are processed individually. The fuzzy learning vector quantization (FLVQ) algorithm we propose generates decision regions (i.e., option classes) divided by ‘intelligent’ classification boundaries. Such an approach improves generalization properties of the MNN model and thereby increases its pricing accuracy.

We develop a dynamic framework to identify aggregate market fears ahead of a major market crash through the skewness premium of European options. Our methodology is based on measuring the distribution of a skewness premium through a q-Gaussian density and a maximum entropy principle. Our findings indicate that the October 19th, 1987 crash was predictable from the study of the skewness premium of deepest out-of-the-money options about two months prior to the crash.

This paper investigates the validity of the random walk theory in the Euro-Serbian dinar exchange rate market. We apply Andrew Lo and Archie MacKinlay's (1988) conventional variance ratio test and Jonathan Wright's (2000) non-parametric ranks and signs based variance ratio tests to the daily Euro/Serbian dinar exchange rate returns using the data from January 2005 - December 2008. Both types of variance ratio tests overwhelmingly reject the random walk hypothesis over the data span. To assess the robustness of our findings, we examine the forecasting performance of a non-linear, nonparametric model in the spirit of Francis Diebold and James Nason (1990) and find that it is able to significantly improve upon the random walk model, thus confirming the existence of foreign exchange market imperfections in a small transition economy such as Serbia. In the last part of the paper, we conduct a comparative study on how our results relate to those of other transition economies in the region.

This paper introduces an entropy approach to measuring market expectations with respect to overnight interest rates in an inter-bank money market. The findings for the Turkish 2000-2001 borrowing crisis suggest that a dynamic, non-extensive entropy framework provides a valuable insight into the degree of aggregate market concerns during the crisis.

This article analyses two sudden depreciations of the Canadian dollar in the 1990s: July/August 1998 and November/December 1994. It is found that a nonparametric exchange rate model based on a combination of fundamental and microstructure (order flow) variables can be used not only to explain, but to also predict such excessive currency movements. During the depreciation periods, the forecast accuracy of the model is significantly superior to that of the linear model. The results provide an illustrative example that order flow variables have a substantial explanatory power for a very short-run exchange rate prediction.

This article tests the profitability of Bollinger Bands (BB) technical indicators. It is found that, after adjusting for transaction costs, the BB are consistently unable to earn profits in excess of the buy-and-hold trading strategy. However, the profitability is improved using a contrarian's approach.

The recent international economics literature suggests that market microstructure effects matter for exchange rate determination and forecasting. This paper investigates performance robustness of the pure microstructure Canada/U.S. dollar exchange rate model. It is found that, when used for forecasting, this microstructure model is very sensitive to the choice of time period and forecasting horizon.

A neuro-fuzzy decision-making technology is designed and implemented to obtain the optimal daily currency trading rule. It is found that a non-linear, artificial neural network exchange rate microstructure (hybrid) model combined with a fuzzy logic controller generates a set of trading strategies that earn a higher rate of return compared to the simple buy-and-hold strategy. After accounting for realistic transaction costs, the gains from utilizing a dynamic, neuro-fuzzy model are still present.

This paper investigates the multiscale (frequency-dependent) relationship between technical trading profitability and feedback trading effects in the Canada/U.S. dollar foreign exchange market. The results suggest weak evidence that technical trading activities of financial and non-financial customers drive frequent violations of the FX market microstructure assumption that exchange rate movements are driven by order flow. After controlling for transaction costs, we find that the contribution of financial customers in feedback trading dominates the contribution of non-financial customers at lower frequencies, while the opposite holds at higher frequencies. In addition, the novel finding is that technical indicators constructed from order flows can be profitable.

This paper concentrates on quantifying the behavioral aspects of systemic risk by using a novel approach based on entropy. More specifically, we study aggregate market expectations and the predictability of the systemic risk before and during the financial crisis in 2008. Two underlying signals for estimating entropic risk measures are considered: 1) skewness premium of deepest out-of-the-money options, and 2) implied volatility ratio in regards to deepest out-of-the-money options. The findings confirm the predictive and contemporaneous usefulness of our entropy setting in market risk management. The degree of predictability is closely linked to both the type of entropy and the nature of the underlying signal.

This article critically investigates the possibility that private information offering systematic profit opportunities exists in the spot foreign exchange market. Using a unique dataset with trader-specific limit and market order histories for more than 10,000 traders, we detect transaction behavior consistent with the informed trading hypothesis, where traders consistently make money. We then work within the theoretical framework of a high-frequency version of a structural microstructure trade model, which directly measures the market maker’s beliefs. Both the estimates of the trade model parameters and our model-free analysis of the data suggest that the time-varying pattern of the probability of informed trading is rooted in the strategic arrival of informed traders on a particular day-of-week, hour-of-day, or geographic location (market). © 2015, Springer-Verlag Berlin Heidelberg.

This paper employs a non-parametric method to forecast high-frequency Canadian/US dollar exchange rate. The introduction of a microstructure variable, order flow, substantially improves the predictive power of both linear and non-linear models. The non-linear models outperform random walk and linear models based on a number of recursive out-of-sample forecasts. Two main criteria that are applied to evaluate model performance are root mean squared error (RMSE) and the ability to predict the direction of exchange rate moves. The artificial neural network (ANN) model is consistently better in RMSE to random walk and linear models for the various out-of-sample set sizes. Moreover, ANN performs better than other models in terms of percentage of correctly predicted exchange rate changes. The empirical results suggest that optimal ANN architecture is superior to random walk and any linear competing model for high-frequency exchange rate forecasting. Copyright © 2006 John Wiley & Sons, Ltd.

This chapter compares the effectiveness of the Black–Scholes option pricing model against a non-parametric alternative during periods of stable economic conditions and periods of financial crises. The results for 1987 and 2008 suggest that the more complicated non-parametric models are more accurate during stable markets than the Black–Scholes model. However, the Black–Scholes model outperforms the non-parametric models during financial crises. These results suggest that a regime switch from stable economic conditions to periods of excessively volatile conditions impedes the estimation and the pricing ability of non-parametric models.

Financial option prices have experienced excessive volatility in response to the recent economic and financial crisis. During the crisis periods, financial markets are, in general, subject to an abrupt regime shift which imposes a significant challenge to option pricing models. In this context, swiftly evolving markets and institutions require valuation models that are capable of recognizing and adapting to such changes. Both parametric and non-parametric pricing models have shown poor forecast ability for options traded in late 1987 and 2008. Surprisingly, the pricing inaccuracy was more pronounced for non-parametric models than for parametric models. To address this problem, we propose a novel hybrid methodology — modular neural network-fuzzy learning vector quantization (MNN-FLVQ) model — that uses the Kohonen unsupervised learning and fuzzy clustering algorithms to classify the S&P 500 stock market index options, and thereby detect a regime shift. In our empirical application, the results for the 2008 financial crisis demonstrate that the MNN-FLVQ model is superior to the competing methods in regards to option pricing during regime shifts.

This paper investigates the multiscale (frequency-dependent) relationship between technical trading profitability and feedback trading effects in the Canada/U.S. dollar foreign exchange market. The results suggest weak evidence that technical trading activities of financial and non-financial customers drive frequent violations of the FX market microstructure assumption that exchange rate movements are driven by order flow. After controlling for transaction costs, we find that the contribution of financial customers in feedback trading dominates the contribution of non-financial customers at lower frequencies, while the opposite holds at higher frequencies. In addition, the novel finding is that technical indicators constructed from order flows can be profitable.

Conventional time series analysis, focusing exclusively on a time series at a given scale, lacks the ability to explain the nature of the data-generating process. A process equation that successfully explains daily price changes, for example, is unable to characterize the nature of hourly price changes. On the other hand, statistical properties of monthly price changes are often not fully covered by a model based on daily price changes. In this paper, we simultaneously model regimes of volatilities at multiple time scales through wavelet-domain hidden Markov models. We establish an important stylized property of volatility across different time scales. We call this property asymmetric vertical dependence. It is asymmetric in the sense that a low volatility state (regime) at a long time horizon is most likely followed by low volatility states at shorter time horizons. On the other hand, a high volatility state at long time horizons does not necessarily imply a high volatility state at shorter time horizons. Our analysis provides evidence that volatility is a mixture of high and low volatility regimes, resulting in a distribution that is non-Gaussian. This result has important implications regarding the scaling behavior of volatility, and, consequently, the calculation of risk at different time scales. © 2010 Taylor & Francis.

Financial option prices have experienced excessive volatility in response to the recent economic and financial crisis. During the crisis periods, financial markets are, in general, subject to an abrupt regime shift which imposes a significant challenge to option pricing models. In this context, swiftly evolving markets and institutions require valuation models that are capable of recognizing and adapting to such changes. Both parametric and non-parametric pricing models have shown poor forecast ability for options traded in late 1987 and 2008. Surprisingly, the pricing inaccuracy was more pronounced for non-parametric models than for parametric models. To address this problem, we propose a novel hybrid methodology - modular neural network-fuzzy learning vector quantization (MNN-FLVQ) model - that uses the Kohonen unsupervised learning and fuzzy clustering algorithms to classify the S&P 500 stock market index options, and thereby detect a regime shift. In our empirical application, the results for the 2008 financial crisis demonstrate that the MNN-FLVQ model is superior to the competing methods in regards to option pricing during regime shifts.

The topic of brand equity continues to be of great importance to private sector firms in the creation and development of both product and company brand strategy. This study analyzes the relationship of different variables and brand equity with the purpose of providing useful insight into brand management and advancement. This research approach is unique in its use of private sector generated measures of brand equity as the main data source. The methodology entails collecting financial information from a list of publicly traded companies evident on the annual Interbrand ranking of top brand values, then executing statistical analysis using correlation and regression. Results make evident a significant positive correlation between brand equity and gross profit, advertising expense, and research and development expense. However, findings reveal that advertising is not as important a driver of brand equity in the short-term as put forward in previous research and evidence suggesting the presence of dynamics and non-linear effects exists.&nbsp

The focus of this paper is to determine the profitability of technical trading rules by evaluating their ability to outperform the naïve buy-and-hold trading strategy. Moving average cross-over rules, filter rules, Bollinger Bands, and trading range break-out rules are tested on the S&P/TSX 300 Index, the Dow Jones Industrial Average Index, NASDAQ Composite Index, and the Canada/U.S. spot exchange rate. After accounting for transaction costs, excess returns are generated by the moving average cross-over rules and trading range break-out rules for the S&P/TSX 300 Index, NASDAQ Composite Index and the Canada/U.S. spot exchange rate. Filter rules also earn excess returns when applied on the Canada/U.S. spot exchange rate. The bootstrap methodology is used to determine the statistical significance of the results. The profitability of the technical trading rules is further enhanced with a combined signal approach.

Given the large body of research addressing exchange rate predictability, the inability of the non-linear model by Diebold and Nason (Journal of International Economics 1990; 28: 315-332) to forecast better than a random walk is puzzling. This paper examines the forecasting performance of Diebold and Nason’s non-parametric model for six major spot Canadian dollar exchange rates for the period 1987-2004. The findings suggest that a more flexible non-parametric estimation technique (artificial neural networks) is required and draw into question the choice of lagged dependent variables as explanatory factors. This paper also proposes a pure microstructure exchange rate model as an alternative to non-linear autoregressive models. Such a model sheds new light on the current evidence on linear/non-linear exchange rate predictability based on market microstructure variables.

The recent growth in the breadth of products sold in electronic commerce markets has created fertile grounds to investigate the Electronic Law of One Price (eLOP). Violations of this law are now more puzzling because many of the traditional frictions should no longer be relevant. This empirical study tests the eLOP by utilizing two datasets with online price data. Pairwise comparison tests reveal that the eLOP does not hold true for any of the product price categories tested.

We explore the relationship between disaggregated trading flows, the Canada/U.S. dollar (CAD/USD) market and U.S. macroeconomic announcements with a novel data set of unprecedented breadth and length. Foreign financial trading flows appear to demand liquidity, contemporaneously driving the CAD/USD while commercial trading flows seem to be price sensitive, providing liquidity in response to exchange rate movements. Despite strong contemporaneous correlations with trading flows, exchange rate returns are generally not predictable, except for some intriguing success at long horizons. This failure contrasts with much, but not all, previous research on the topic. While two types of CAD trading flows and the CAD/USD appear to be cointegrated, such structure is probably spurious. There appear to be structural breaks in the order-flow-exchange rate VECM systems in 1994-1996 and 1998-1999.

This paper develops a wavelet (spectral) approach to estimate the parameters of a linear regression model where the regressand and the regressors are persistent processes and contain a measurement error. We propose a wavelet filtering approach which does not require instruments and yields unbiased and consistent estimates for the intercept and the slope parameters. Our Monte Carlo results also show that the wavelet approach is particularly effective when measurement errors for the regressand and the regressor are serially correlated. With this paper, we hope to bring a fresh perspective and stimulate further theoretical research in this area.

We examine a recent high-frequency spot EUR-USD foreign exchange transaction data from an electronic foreign exchange market. Our framework is based on a continuous time sequential microstructure trade model which measures the market maker's beliefs directly. We present evidence of the strategic arrival of informed traders on a particular day-of-week, time-of-day and geographic location (market).

We explore the relationship between disaggregated order flow, the Canada/U.S. dollar (CAD/USD) market and U.S. macroeconomic announcements. Three types of CAD order flow and the CAD/USD are cointegrated. Financial order flow appears to contemporaneously drive the CAD/USD while commercial order flow seems to contemporaneously respond to exchange rate movements. Past order flow and lagged exchange rates strongly explain most types of order flow. Despite this predictability and the contemporaneous correlation of order flow with exchange rate returns, exchange rate returns are not predictable by either statistical or economic criteria (trading rule). This negative finding contrasts with that of Rime et al (2007), who use a different data set. There is strong evidence of structural breaks in the order-flow-exchange rate systems in 1994, 1996-1997 and 1999-2000.